Initial commit

README.md

@@ -6,7 +6,7 @@ tags:
 - reinforcement-learning
 - stable-baselines3
 model-index:
-- name: A2C
+- name: DDPG
   results:
   - task:
       type: reinforcement-learning
@@ -16,13 +16,13 @@ model-index:
       type: PandaPickAndPlace-v3
     metrics:
     - type: mean_reward
-      value: -45.00 +/- 15.00
+      value: -50.00 +/- 0.00
       name: mean_reward
       verified: false
 ---
 
-# **A2C** Agent playing **PandaPickAndPlace-v3**
-This is a trained model of a **A2C** agent playing **PandaPickAndPlace-v3**
+# **DDPG** Agent playing **PandaPickAndPlace-v3**
+This is a trained model of a **DDPG** agent playing **PandaPickAndPlace-v3**
 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
 
 ## Usage (with Stable-baselines3)

config.json

@@ -1 +1 @@
-{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVRQAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMG011bHRpSW5wdXRBY3RvckNyaXRpY1BvbGljeZSTlC4=", "__module__": "stable_baselines3.common.policies", "__doc__": "\n    MultiInputActorClass policy class for actor-critic algorithms (has both policy and value prediction).\n    Used by A2C, PPO and the likes.\n\n    :param observation_space: Observation space (Tuple)\n    :param action_space: Action space\n    :param lr_schedule: Learning rate schedule (could be constant)\n    :param net_arch: The specification of the policy and value networks.\n    :param activation_fn: Activation function\n    :param ortho_init: Whether to use or not orthogonal initialization\n    :param use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param full_std: Whether to use (n_features x n_actions) parameters\n        for the std instead of only (n_features,) when using gSDE\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n        a positive standard deviation (cf paper). It allows to keep variance\n        above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n    :param squash_output: Whether to squash the output using a tanh function,\n        this allows to ensure boundaries when using gSDE.\n    :param features_extractor_class: Uses the CombinedExtractor\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\n    :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n    :param normalize_images: Whether to normalize images or not,\n         dividing by 255.0 (True by default)\n    :param optimizer_class: The optimizer to use,\n        ``th.optim.Adam`` by default\n    :param optimizer_kwargs: Additional keyword arguments,\n        excluding the learning rate, to pass to the optimizer\n    ", "__init__": "<function MultiInputActorCriticPolicy.__init__ at 0x7fd67e4ddea0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fd67e4dae40>"}, "verbose": 1, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gAWVgQAAAAAAAAB9lCiMD29wdGltaXplcl9jbGFzc5SME3RvcmNoLm9wdGltLnJtc3Byb3CUjAdSTVNwcm9wlJOUjBBvcHRpbWl6ZXJfa3dhcmdzlH2UKIwFYWxwaGGURz/vrhR64UeujANlcHOURz7k+LWI42jxjAx3ZWlnaHRfZGVjYXmUSwB1dS4=", "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>", "optimizer_kwargs": {"alpha": 0.99, "eps": 1e-05, "weight_decay": 0}}, "num_timesteps": 1000000, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1708877771849107846, "learning_rate": 0.0007, "tensorboard_log": null, "_last_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[-0.3410083   0.63062656  0.09819238]\n [-0.8633413   0.95956427  0.09818147]\n [ 0.01721932  0.42921337  0.09818147]\n [-0.2499784   0.5423469   0.09816843]]", "desired_goal": "[[-0.84529305 -0.89026105  1.2078592 ]\n [ 0.43892425  0.59937584  1.1962022 ]\n [-1.3590631   1.4967892  -0.26726732]\n [ 0.28802958  1.1857473  -1.0880407 ]]", "observation": "[[ 9.2136174e-02 -4.2665582e-03  1.6705894e-01 -1.1053880e+00\n   2.2375207e-01 -7.2122288e-01  9.4586378e-01 -3.4100831e-01\n   6.3062656e-01  9.8192379e-02 -2.8656614e-03  2.4323097e-04\n  -1.6716018e-02  1.9766789e-02  2.0162044e-03  4.7854099e-02\n  -2.1571419e-03 -1.7149510e-02 -5.8596414e-03]\n [-1.6409372e+00 -3.6592728e-01  5.2202433e-01  1.5759315e+00\n   1.6634192e+00  8.7472123e-01  1.2118865e+00 -8.6334127e-01\n   9.5956427e-01  9.8181471e-02 -2.9662647e-03  4.7755026e-04\n  -1.7125709e-02  2.0097023e-02  1.3767199e-03  4.8108198e-02\n   4.1026372e-04 -1.5528759e-02 -6.0134674e-03]\n [-7.1983969e-01 -2.3859921e-01  2.8656125e-01  1.1090955e+00\n  -2.0051996e-01  3.5049042e-01  1.1795807e+00  1.7219324e-02\n   4.2921337e-01  9.8181471e-02 -2.9662645e-03  4.7754840e-04\n  -1.6892739e-02  2.0097028e-02  1.3767103e-03  4.8108198e-02\n   4.1026372e-04 -1.5528759e-02 -6.0134353e-03]\n [ 1.4153056e-01  4.9065158e-02  4.8176584e-01 -2.4587384e-01\n  -3.9117819e-01 -9.4231087e-01 -9.7623879e-01 -2.4997839e-01\n   5.4234689e-01  9.8168425e-02 -2.6174244e-03  2.7405002e-04\n  -1.7017271e-02  1.9845013e-02  1.4869155e-03  4.8108198e-02\n   4.1026407e-04 -1.5528759e-02 -6.0288482e-03]]"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[ 0.1318048  -0.07619794  0.02      ]\n [-0.03798684  0.09140378  0.02      ]\n [-0.09794831  0.05327327  0.02      ]\n [-0.08871158  0.1389011   0.02      ]]", "desired_goal": "[[ 0.08143605 -0.03330576  0.05269539]\n [ 0.06488575  0.05030977  0.18453664]\n [ 0.03297789 -0.01518581  0.03180234]\n [-0.02484735 -0.08769     0.02      ]]", "observation": "[[ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00  0.0000000e+00  1.3180479e-01\n  -7.6197945e-02  2.0000000e-02  0.0000000e+00 -0.0000000e+00\n   0.0000000e+00  0.0000000e+00  0.0000000e+00  0.0000000e+00\n   0.0000000e+00  0.0000000e+00  0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00  0.0000000e+00 -3.7986845e-02\n   9.1403782e-02  2.0000000e-02  0.0000000e+00 -0.0000000e+00\n   0.0000000e+00  0.0000000e+00  0.0000000e+00  0.0000000e+00\n   0.0000000e+00  0.0000000e+00  0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00  0.0000000e+00 -9.7948313e-02\n   5.3273272e-02  2.0000000e-02  0.0000000e+00 -0.0000000e+00\n   0.0000000e+00  0.0000000e+00  0.0000000e+00  0.0000000e+00\n   0.0000000e+00  0.0000000e+00  0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00  0.0000000e+00 -8.8711582e-02\n   1.3890110e-01  2.0000000e-02  0.0000000e+00 -0.0000000e+00\n   0.0000000e+00  0.0000000e+00  0.0000000e+00  0.0000000e+00\n   0.0000000e+00  0.0000000e+00  0.0000000e+00]]"}, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 0.0, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWV4AsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHwEkAAAAAAACMAWyUSzKMAXSUR0ClU7BSUC7sdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClU6BfKISEdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClU0yGrS3LdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClU95IH1OCdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClVL5Z8rqddX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClVKvxhDw6dX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClVFCbc45tdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClVNhvrGBGdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClVbtfXwsodX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClVaZdOZb7dX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClVUkhA4XGdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClVc2cz67/dX2UKGgGRwAAAAAAAAAAaAdLAWgIR0ClVdKeK8+SdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClVrP69CeFdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClVqB6a9bpdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClVkYcm0E6dX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClVtU34sVddX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClV7BTfixWdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClV57x3FDOdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClV0JpFkQPdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClV8uF6AvtdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClWK1iF0xNdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClWJe+mFajdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClWDkGqxTsdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClWMcRL9MsdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClWaAkcCHRdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClWY3qJMxodX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClWTAbADaHdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClWbf8uSOjdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClWpbnX/YKdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClWoGpMpPRdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClWiKLbYbsdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClWquJUHY6dX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClW4Sz5XU6dX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClW4p9qk/KdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClW1FIVdondX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClW+ocJdB0dX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClXOl2V3UydX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClXOw1aW5ZdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClXLmIsRQKdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClXVF5v99/dX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClXkiMHbAUdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClXk/zreImdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClXiAam4y5dX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClXsEroW56dX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClX8jFZPl/dX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClX8TuF6AwdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClX2FLFn7IdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClX+hN/OMVdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClYMIbGWD6dX2UKGgGRwAAAAAAAAAAaAdLAWgIR0ClYMmYrrgPdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClYLDvVmSRdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClYFLFwT/RdX2UKGgGRwAAAAAAAAAAaAdLAWgIR0ClYFctf5UMdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClYNuhkAggdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClYbwWepXIdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClYaKR2bG4dX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClYUagM+eOdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClYc0YKpkxdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClYqmKqGUOdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClYpmCZnctdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClYjxNh3JQdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClYr/GuLaVdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClY52QXAM2dX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClY4P1ct5EdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClYyxgJC0GdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClY7A8r7O3dX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClZI0g0TDgdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClZHUedTYNdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClZB2Ebo8qdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClZKBqbjLkdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClZYILofSydX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClZWkeQuEmdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClZRM5GSZCdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClZZh2wFC+dX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClZnditq59dX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClZmTCUHIIdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClZhUjC53DdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClZpzeoDPodX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClZ3vHktEodX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClZ2BegL7XdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClZwgFgUlBdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClZ4xREWqMdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClaG1uBMBZdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClaFHGKhtcdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClZ/X+2mYTdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClaH5mI0qIdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClaVxL9MsZdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClaUZtFa0QdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClaOy4FzMidX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClaXA/9pAVdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0Clak4cvM8pdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClajUelsP8dX2UKGgGR8BJAAAAAAAAaAdLMmgIR0Clad1jI7vHdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClamG3OObRdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0Cla0hpYcNpdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0Clazm4AjptdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClauxlxwQ2dX2UKGgGR8BJAAAAAAAAaAdLMmgIR0Cla2/apPykdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0ClbE0jTrmhdWUu"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 50000, "n_steps": 5, "gamma": 0.99, "gae_lambda": 1.0, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "rollout_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOgAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwRRGljdFJvbGxvdXRCdWZmZXKUk5Qu", "__module__": "stable_baselines3.common.buffers", "__annotations__": "{'observation_space': <class 'gymnasium.spaces.dict.Dict'>, 'obs_shape': typing.Dict[str, typing.Tuple[int, ...]], 'observations': typing.Dict[str, numpy.ndarray]}", "__doc__": "\n    Dict Rollout buffer used in on-policy algorithms like A2C/PPO.\n    Extends the RolloutBuffer to use dictionary observations\n\n    It corresponds to ``buffer_size`` transitions collected\n    using the current policy.\n    This experience will be discarded after the policy update.\n    In order to use PPO objective, we also store the current value of each state\n    and the log probability of each taken action.\n\n    The term rollout here refers to the model-free notion and should not\n    be used with the concept of rollout used in model-based RL or planning.\n    Hence, it is only involved in policy and value function training but not action selection.\n\n    :param buffer_size: Max number of element in the buffer\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param device: PyTorch device\n    :param gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n        Equivalent to Monte-Carlo advantage estimate when set to 1.\n    :param gamma: Discount factor\n    :param n_envs: Number of parallel environments\n    ", "__init__": "<function DictRolloutBuffer.__init__ at 0x7fd67e63c820>", "reset": "<function DictRolloutBuffer.reset at 0x7fd67e63c8b0>", "add": "<function DictRolloutBuffer.add at 0x7fd67e63c940>", "get": "<function DictRolloutBuffer.get at 0x7fd67e63c9d0>", "_get_samples": "<function DictRolloutBuffer._get_samples at 0x7fd67e63ca60>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fd67e631640>"}, "rollout_buffer_kwargs": {}, "normalize_advantage": false, "observation_space": {":type:": "<class 'gymnasium.spaces.dict.Dict'>", ":serialized:": "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", "spaces": "OrderedDict([('achieved_goal', Box(-10.0, 10.0, (3,), float32)), ('desired_goal', Box(-10.0, 10.0, (3,), float32)), ('observation', Box(-10.0, 10.0, (19,), float32))])", "_shape": null, "dtype": null, "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True  True]", "bounded_above": "[ True  True  True  True]", "_shape": [4], "low": "[-1. -1. -1. -1.]", "high": "[1. 1. 1. 1.]", "low_repr": "-1.0", "high_repr": "1.0", "_np_random": null}, "n_envs": 4, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuDQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz9G8AaNuLrHhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "system_info": {"OS": "Linux-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.2.1", "PyTorch": "2.1.0+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.29.1", "OpenAI Gym": "0.25.2"}}
+{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVNwAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLnRkMy5wb2xpY2llc5SMEE11bHRpSW5wdXRQb2xpY3mUk5Qu", "__module__": "stable_baselines3.td3.policies", "__doc__": "\n    Policy class (with both actor and critic) for TD3 to be used with Dict observation spaces.\n\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param lr_schedule: Learning rate schedule (could be constant)\n    :param net_arch: The specification of the policy and value networks.\n    :param activation_fn: Activation function\n    :param features_extractor_class: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\n    :param normalize_images: Whether to normalize images or not,\n         dividing by 255.0 (True by default)\n    :param optimizer_class: The optimizer to use,\n        ``th.optim.Adam`` by default\n    :param optimizer_kwargs: Additional keyword arguments,\n        excluding the learning rate, to pass to the optimizer\n    :param n_critics: Number of critic networks to create.\n    :param share_features_extractor: Whether to share or not the features extractor\n        between the actor and the critic (this saves computation time)\n    ", "__init__": "<function MultiInputPolicy.__init__ at 0x7d585e1495a0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7d585e14c140>"}, "verbose": 1, "policy_kwargs": {"net_arch": [256, 256, 256], "n_critics": 1}, "num_timesteps": 1000050, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": {":type:": "<class 'stable_baselines3.common.noise.NormalActionNoise'>", ":serialized:": "gAWVMQEAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5ub2lzZZSMEU5vcm1hbEFjdGlvbk5vaXNllJOUKYGUfZQojANfbXWUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWIAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAJSMBW51bXB5lIwFZHR5cGWUk5SMAmY4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLBIWUjAFDlHSUUpSMBl9zaWdtYZRoCCiWIAAAAAAAAACamZmZmZnJP5qZmZmZmck/mpmZmZmZyT+amZmZmZnJP5RoD0sEhZRoE3SUUpSMBl9kdHlwZZRoCowHZmxvYXQzMpSTlHViLg==", "_mu": "[0. 0. 0. 0.]", "_sigma": "[0.2 0.2 0.2 0.2]", "_dtype": "<class 'numpy.float32'>"}, "start_time": 1709010350043990555, "learning_rate": 0.001, "tensorboard_log": "runs/DDPGPandaPickandPlacev3", "_last_obs": null, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "gAWVXwEAAAAAAACMC2NvbGxlY3Rpb25zlIwLT3JkZXJlZERpY3SUk5QpUpQojA1hY2hpZXZlZF9nb2FslIwSbnVtcHkuY29yZS5udW1lcmljlIwLX2Zyb21idWZmZXKUk5QolgwAAAAAAAAAZpTRPUsTgj0K16M8lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwOGlIwBQ5R0lFKUjAxkZXNpcmVkX2dvYWyUaAcolgwAAAAAAAAAJP4CPvVjED6rFQI+lGgOSwFLA4aUaBJ0lFKUjAtvYnNlcnZhdGlvbpRoByiWTAAAAAAAAADqch09GWwarEMjSj4AAAAAAAAAgAAAAAAAAAAAZpTRPUsTgj0K16M8AAAAAAAAAIAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlGgOSwFLE4aUaBJ0lFKUdS4=", "achieved_goal": "[[0.10233383 0.06351336 0.02      ]]", "desired_goal": "[[0.1279226  0.1410063  0.12703578]]", "observation": "[[ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00  0.0000000e+00  1.0233383e-01\n   6.3513361e-02  2.0000000e-02  0.0000000e+00 -0.0000000e+00\n   0.0000000e+00  0.0000000e+00  0.0000000e+00  0.0000000e+00\n   0.0000000e+00  0.0000000e+00  0.0000000e+00]]"}, "_episode_num": 20459, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -5.0000000000105516e-05, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVhgAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKImJiYmJiYmJiYmJiYmJiYmJiYmJiYmIiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYllLg=="}, "_n_updates": 999950, "observation_space": {":type:": "<class 'gymnasium.spaces.dict.Dict'>", ":serialized:": "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", "spaces": "OrderedDict([('achieved_goal', Box(-10.0, 10.0, (3,), float32)), ('desired_goal', Box(-10.0, 10.0, (3,), float32)), ('observation', Box(-10.0, 10.0, (19,), float32))])", "_shape": null, "dtype": null, "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True  True]", "bounded_above": "[ True  True  True  True]", "_shape": [4], "low": "[-1. -1. -1. -1.]", "high": "[1. 1. 1. 1.]", "low_repr": "-1.0", "high_repr": "1.0", "_np_random": "Generator(PCG64)"}, "n_envs": 1, "buffer_size": 1000000, "batch_size": 256, "learning_starts": 100, "tau": 0.95, "gamma": 0.99, "gradient_steps": -1, "optimize_memory_usage": false, "replay_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVPwAAAAAAAACMJ3N0YWJsZV9iYXNlbGluZXMzLmhlci5oZXJfcmVwbGF5X2J1ZmZlcpSMD0hlclJlcGxheUJ1ZmZlcpSTlC4=", "__module__": "stable_baselines3.her.her_replay_buffer", "__annotations__": "{'env': typing.Optional[stable_baselines3.common.vec_env.base_vec_env.VecEnv]}", "__doc__": "\n    Hindsight Experience Replay (HER) buffer.\n    Paper: https://arxiv.org/abs/1707.01495\n\n    Replay buffer for sampling HER (Hindsight Experience Replay) transitions.\n\n    .. note::\n\n      Compared to other implementations, the ``future`` goal sampling strategy is inclusive:\n      the current transition can be used when re-sampling.\n\n    :param buffer_size: Max number of element in the buffer\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param env: The training environment\n    :param device: PyTorch device\n    :param n_envs: Number of parallel environments\n    :param optimize_memory_usage: Enable a memory efficient variant\n        Disabled for now (see https://github.com/DLR-RM/stable-baselines3/pull/243#discussion_r531535702)\n    :param handle_timeout_termination: Handle timeout termination (due to timelimit)\n        separately and treat the task as infinite horizon task.\n        https://github.com/DLR-RM/stable-baselines3/issues/284\n    :param n_sampled_goal: Number of virtual transitions to create per real transition,\n        by sampling new goals.\n    :param goal_selection_strategy: Strategy for sampling goals for replay.\n        One of ['episode', 'final', 'future']\n    :param copy_info_dict: Whether to copy the info dictionary and pass it to\n        ``compute_reward()`` method.\n        Please note that the copy may cause a slowdown.\n        False by default.\n    ", "__init__": "<function HerReplayBuffer.__init__ at 0x7d585e14a200>", "__getstate__": "<function HerReplayBuffer.__getstate__ at 0x7d585e14a290>", "__setstate__": "<function HerReplayBuffer.__setstate__ at 0x7d585e14a320>", "set_env": "<function HerReplayBuffer.set_env at 0x7d585e14a3b0>", "add": "<function HerReplayBuffer.add at 0x7d585e14a440>", "_compute_episode_length": "<function HerReplayBuffer._compute_episode_length at 0x7d585e14a4d0>", "sample": "<function HerReplayBuffer.sample at 0x7d585e14a560>", "_get_real_samples": "<function HerReplayBuffer._get_real_samples at 0x7d585e14a5f0>", "_get_virtual_samples": "<function HerReplayBuffer._get_virtual_samples at 0x7d585e14a680>", "_sample_goals": "<function HerReplayBuffer._sample_goals at 0x7d585e14a710>", "truncate_last_trajectory": "<function HerReplayBuffer.truncate_last_trajectory at 0x7d585e14a7a0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7d585e14f400>"}, "replay_buffer_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gAWVggAAAAAAAAB9lCiMDm5fc2FtcGxlZF9nb2FslEsEjBdnb2FsX3NlbGVjdGlvbl9zdHJhdGVneZSMLXN0YWJsZV9iYXNlbGluZXMzLmhlci5nb2FsX3NlbGVjdGlvbl9zdHJhdGVneZSMFUdvYWxTZWxlY3Rpb25TdHJhdGVneZSTlEsAhZRSlHUu", "n_sampled_goal": 4, "goal_selection_strategy": "GoalSelectionStrategy.FUTURE"}, "train_freq": {":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>", ":serialized:": "gAWVZAAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMB2VwaXNvZGWUhZRSlIaUgZQu"}, "use_sde_at_warmup": false, "policy_delay": 1, "target_noise_clip": 0.0, "target_policy_noise": 0.1, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "actor_batch_norm_stats": [], "critic_batch_norm_stats": [], "actor_batch_norm_stats_target": [], "critic_batch_norm_stats_target": [], "system_info": {"OS": "Linux-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.2.1", "PyTorch": "2.1.0+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.29.1", "OpenAI Gym": "0.25.2"}}

ddpg-PandaPickAndPlace-v3.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df7ad916bc8175a35a16279d5627df9ece26fbf9b73209f9a31a5527e6d4a3c4
+size 4505895

ddpg-PandaPickAndPlace-v3/_stable_baselines3_version

@@ -0,0 +1 @@
+2.2.1

ddpg-PandaPickAndPlace-v3/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6a891d5852b2a68436a1e432f1f329aeb3a90a56ce8f6fd588116cb61ac0faa
+size 1121102

ddpg-PandaPickAndPlace-v3/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:041fc285637c2765a09601396de8f7d82830e7be8d0008aa38490a3940a5c5c0
+size 1123150

ddpg-PandaPickAndPlace-v3/data

@@ -0,0 +1,133 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVNwAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLnRkMy5wb2xpY2llc5SMEE11bHRpSW5wdXRQb2xpY3mUk5Qu",
+        "__module__": "stable_baselines3.td3.policies",
+        "__doc__": "\n    Policy class (with both actor and critic) for TD3 to be used with Dict observation spaces.\n\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param lr_schedule: Learning rate schedule (could be constant)\n    :param net_arch: The specification of the policy and value networks.\n    :param activation_fn: Activation function\n    :param features_extractor_class: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\n    :param normalize_images: Whether to normalize images or not,\n         dividing by 255.0 (True by default)\n    :param optimizer_class: The optimizer to use,\n        ``th.optim.Adam`` by default\n    :param optimizer_kwargs: Additional keyword arguments,\n        excluding the learning rate, to pass to the optimizer\n    :param n_critics: Number of critic networks to create.\n    :param share_features_extractor: Whether to share or not the features extractor\n        between the actor and the critic (this saves computation time)\n    ",
+        "__init__": "<function MultiInputPolicy.__init__ at 0x7d585e1495a0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7d585e14c140>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "net_arch": [
+            256,
+            256,
+            256
+        ],
+        "n_critics": 1
+    },
+    "num_timesteps": 1000050,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": {
+        ":type:": "<class 'stable_baselines3.common.noise.NormalActionNoise'>",
+        ":serialized:": "gAWVMQEAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5ub2lzZZSMEU5vcm1hbEFjdGlvbk5vaXNllJOUKYGUfZQojANfbXWUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWIAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAJSMBW51bXB5lIwFZHR5cGWUk5SMAmY4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLBIWUjAFDlHSUUpSMBl9zaWdtYZRoCCiWIAAAAAAAAACamZmZmZnJP5qZmZmZmck/mpmZmZmZyT+amZmZmZnJP5RoD0sEhZRoE3SUUpSMBl9kdHlwZZRoCowHZmxvYXQzMpSTlHViLg==",
+        "_mu": "[0. 0. 0. 0.]",
+        "_sigma": "[0.2 0.2 0.2 0.2]",
+        "_dtype": "<class 'numpy.float32'>"
+    },
+    "start_time": 1709010350043990555,
+    "learning_rate": 0.001,
+    "tensorboard_log": "runs/DDPGPandaPickandPlacev3",
+    "_last_obs": null,
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'collections.OrderedDict'>",
+        ":serialized:": "gAWVXwEAAAAAAACMC2NvbGxlY3Rpb25zlIwLT3JkZXJlZERpY3SUk5QpUpQojA1hY2hpZXZlZF9nb2FslIwSbnVtcHkuY29yZS5udW1lcmljlIwLX2Zyb21idWZmZXKUk5QolgwAAAAAAAAAZpTRPUsTgj0K16M8lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwOGlIwBQ5R0lFKUjAxkZXNpcmVkX2dvYWyUaAcolgwAAAAAAAAAJP4CPvVjED6rFQI+lGgOSwFLA4aUaBJ0lFKUjAtvYnNlcnZhdGlvbpRoByiWTAAAAAAAAADqch09GWwarEMjSj4AAAAAAAAAgAAAAAAAAAAAZpTRPUsTgj0K16M8AAAAAAAAAIAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlGgOSwFLE4aUaBJ0lFKUdS4=",
+        "achieved_goal": "[[0.10233383 0.06351336 0.02      ]]",
+        "desired_goal": "[[0.1279226  0.1410063  0.12703578]]",
+        "observation": "[[ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00  0.0000000e+00  1.0233383e-01\n   6.3513361e-02  2.0000000e-02  0.0000000e+00 -0.0000000e+00\n   0.0000000e+00  0.0000000e+00  0.0000000e+00  0.0000000e+00\n   0.0000000e+00  0.0000000e+00  0.0000000e+00]]"
+    },
+    "_episode_num": 20459,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -5.0000000000105516e-05,
+    "_stats_window_size": 100,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVhgAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKImJiYmJiYmJiYmJiYmJiYmJiYmJiYmIiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYllLg=="
+    },
+    "_n_updates": 999950,
+    "observation_space": {
+        ":type:": "<class 'gymnasium.spaces.dict.Dict'>",
+        ":serialized:": "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",
+        "spaces": "OrderedDict([('achieved_goal', Box(-10.0, 10.0, (3,), float32)), ('desired_goal', Box(-10.0, 10.0, (3,), float32)), ('observation', Box(-10.0, 10.0, (19,), float32))])",
+        "_shape": null,
+        "dtype": null,
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "bounded_below": "[ True  True  True  True]",
+        "bounded_above": "[ True  True  True  True]",
+        "_shape": [
+            4
+        ],
+        "low": "[-1. -1. -1. -1.]",
+        "high": "[1. 1. 1. 1.]",
+        "low_repr": "-1.0",
+        "high_repr": "1.0",
+        "_np_random": "Generator(PCG64)"
+    },
+    "n_envs": 1,
+    "buffer_size": 1000000,
+    "batch_size": 256,
+    "learning_starts": 100,
+    "tau": 0.95,
+    "gamma": 0.99,
+    "gradient_steps": -1,
+    "optimize_memory_usage": false,
+    "replay_buffer_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVPwAAAAAAAACMJ3N0YWJsZV9iYXNlbGluZXMzLmhlci5oZXJfcmVwbGF5X2J1ZmZlcpSMD0hlclJlcGxheUJ1ZmZlcpSTlC4=",
+        "__module__": "stable_baselines3.her.her_replay_buffer",
+        "__annotations__": "{'env': typing.Optional[stable_baselines3.common.vec_env.base_vec_env.VecEnv]}",
+        "__doc__": "\n    Hindsight Experience Replay (HER) buffer.\n    Paper: https://arxiv.org/abs/1707.01495\n\n    Replay buffer for sampling HER (Hindsight Experience Replay) transitions.\n\n    .. note::\n\n      Compared to other implementations, the ``future`` goal sampling strategy is inclusive:\n      the current transition can be used when re-sampling.\n\n    :param buffer_size: Max number of element in the buffer\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param env: The training environment\n    :param device: PyTorch device\n    :param n_envs: Number of parallel environments\n    :param optimize_memory_usage: Enable a memory efficient variant\n        Disabled for now (see https://github.com/DLR-RM/stable-baselines3/pull/243#discussion_r531535702)\n    :param handle_timeout_termination: Handle timeout termination (due to timelimit)\n        separately and treat the task as infinite horizon task.\n        https://github.com/DLR-RM/stable-baselines3/issues/284\n    :param n_sampled_goal: Number of virtual transitions to create per real transition,\n        by sampling new goals.\n    :param goal_selection_strategy: Strategy for sampling goals for replay.\n        One of ['episode', 'final', 'future']\n    :param copy_info_dict: Whether to copy the info dictionary and pass it to\n        ``compute_reward()`` method.\n        Please note that the copy may cause a slowdown.\n        False by default.\n    ",
+        "__init__": "<function HerReplayBuffer.__init__ at 0x7d585e14a200>",
+        "__getstate__": "<function HerReplayBuffer.__getstate__ at 0x7d585e14a290>",
+        "__setstate__": "<function HerReplayBuffer.__setstate__ at 0x7d585e14a320>",
+        "set_env": "<function HerReplayBuffer.set_env at 0x7d585e14a3b0>",
+        "add": "<function HerReplayBuffer.add at 0x7d585e14a440>",
+        "_compute_episode_length": "<function HerReplayBuffer._compute_episode_length at 0x7d585e14a4d0>",
+        "sample": "<function HerReplayBuffer.sample at 0x7d585e14a560>",
+        "_get_real_samples": "<function HerReplayBuffer._get_real_samples at 0x7d585e14a5f0>",
+        "_get_virtual_samples": "<function HerReplayBuffer._get_virtual_samples at 0x7d585e14a680>",
+        "_sample_goals": "<function HerReplayBuffer._sample_goals at 0x7d585e14a710>",
+        "truncate_last_trajectory": "<function HerReplayBuffer.truncate_last_trajectory at 0x7d585e14a7a0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7d585e14f400>"
+    },
+    "replay_buffer_kwargs": {
+        ":type:": "<class 'dict'>",
+        ":serialized:": "gAWVggAAAAAAAAB9lCiMDm5fc2FtcGxlZF9nb2FslEsEjBdnb2FsX3NlbGVjdGlvbl9zdHJhdGVneZSMLXN0YWJsZV9iYXNlbGluZXMzLmhlci5nb2FsX3NlbGVjdGlvbl9zdHJhdGVneZSMFUdvYWxTZWxlY3Rpb25TdHJhdGVneZSTlEsAhZRSlHUu",
+        "n_sampled_goal": 4,
+        "goal_selection_strategy": "GoalSelectionStrategy.FUTURE"
+    },
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gAWVZAAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMB2VwaXNvZGWUhZRSlIaUgZQu"
+    },
+    "use_sde_at_warmup": false,
+    "policy_delay": 1,
+    "target_noise_clip": 0.0,
+    "target_policy_noise": 0.1,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "actor_batch_norm_stats": [],
+    "critic_batch_norm_stats": [],
+    "actor_batch_norm_stats_target": [],
+    "critic_batch_norm_stats_target": []
+}

ddpg-PandaPickAndPlace-v3/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27868ffae798fb58c4a52007d6e20e127d4ecf0eebd74e0b4cc7866ea816a7c7
+size 2242742

ddpg-PandaPickAndPlace-v3/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c35cea3b2e60fb5e7e162d3592df775cd400e575a31c72f359fb9e654ab00c5
+size 864

ddpg-PandaPickAndPlace-v3/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023
+- Python: 3.10.12
+- Stable-Baselines3: 2.2.1
+- PyTorch: 2.1.0+cu121
+- GPU Enabled: True
+- Numpy: 1.25.2
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.29.1
+- OpenAI Gym: 0.25.2

results.json

@@ -1 +1 @@
-{"mean_reward": -45.0, "std_reward": 15.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-02-25T17:11:40.264986"}
+{"mean_reward": -50.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-02-27T09:28:46.728666"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ec211ae9a6f797f48790f27d12819f2668f5052652b7255ce2009bf39be8cd5
-size 3046
+oid sha256:4aa7ac7f98751ac563d4427e2603b2bf0356ab672ba149f75251ee08f14d2c5a
+size 3230