Initial commit

A2C-PandaPickAndPlaceDense-v3.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4e6b1b14c6b2fff1426ad99ef27bfe2f91d1dd25a41e8ba4d2486bcb6c4cfc5
+size 120554

A2C-PandaPickAndPlaceDense-v3/_stable_baselines3_version

@@ -0,0 +1 @@
+2.0.0a5

A2C-PandaPickAndPlaceDense-v3/data

@@ -0,0 +1,97 @@
+{
+    "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 0x0000021C7CE91620>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x0000021C7CE8A580>"
+    },
+    "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": 1000,
+    "_total_timesteps": 1000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1714989079990673900,
+    "learning_rate": 0.0007,
+    "tensorboard_log": null,
+    "_last_obs": {
+        ":type:": "<class 'collections.OrderedDict'>",
+        ":serialized:": "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",
+        "achieved_goal": "[[ 1.3044112   0.7683268   0.12032255]\n [-0.66273177 -0.3659164   0.12032255]\n [ 0.6235068  -0.47585195  0.12032255]\n [-0.24543248  0.64232     0.12032255]]",
+        "desired_goal": "[[ 1.8122001   1.5443218  -1.3811198 ]\n [ 0.879466    1.1630942   1.6339891 ]\n [-0.3728456  -1.1283029   1.804592  ]\n [-0.8088598  -0.37469706 -1.3811198 ]]",
+        "observation": "[[ 0.5842109  -0.4916305   1.4156107   0.09762286 -0.02797361  0.11328804\n  -1.0602591   1.3044112   0.7683268   0.12032255 -0.03702876  0.2058336\n   0.03976776  0.14498791  0.08506173  0.07189737 -0.07872247 -0.00202583\n   0.08094105]\n [ 0.5842109  -0.4916305   1.4156107   0.09762286 -0.02797361  0.11328804\n  -1.0602591  -0.66273177 -0.3659164   0.12032255 -0.03702876  0.2058336\n   0.03976776  0.14498791  0.08506173  0.07189737 -0.07872247 -0.00202583\n   0.08094105]\n [ 0.5842109  -0.4916305   1.4156107   0.09762286 -0.02797361  0.11328804\n  -1.0602591   0.6235068  -0.47585195  0.12032255 -0.03702876  0.2058336\n   0.03976776  0.14498791  0.08506173  0.07189737 -0.07872247 -0.00202583\n   0.08094105]\n [ 0.5842109  -0.4916305   1.4156107   0.09762286 -0.02797361  0.11328804\n  -1.0602591  -0.24543248  0.64232     0.12032255 -0.03702876  0.2058336\n   0.03976776  0.14498791  0.08506173  0.07189737 -0.07872247 -0.00202583\n   0.08094105]]"
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAEBAQGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'collections.OrderedDict'>",
+        ":serialized:": "gAWViwIAAAAAAACMC2NvbGxlY3Rpb25zlIwLT3JkZXJlZERpY3SUk5QpUpQojA1hY2hpZXZlZF9nb2FslIwSbnVtcHkuY29yZS5udW1lcmljlIwLX2Zyb21idWZmZXKUk5QoljAAAAAAAAAAGXRWPP9Spj0K16M8VmcXPmzJAr4K16M8GoNAvHV4hz0K16M8SY8AvoKKEb0K16M8lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksESwOGlIwBQ5R0lFKUjAxkZXNpcmVkX2dvYWyUaAcoljAAAAAAAAAAKpNUPZM5/j048zI9J5jfPUi7BT7iYyE+RE6+vYLM2D0Ys1E+POg6PZas5L3xhcs9lGgOSwRLA4aUaBJ0lFKUjAtvYnNlcnZhdGlvbpRoByiWMAEAAAAAAADqch09GWwarEMjSj4AAAAAAAAAgAAAAAAAAAAAGXRWPP9Spj0K16M8AAAAAAAAAIAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA6nIdPRlsGqxDI0o+AAAAAAAAAIAAAAAAAAAAAFZnFz5syQK+CtejPAAAAAAAAACAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAOpyHT0ZbBqsQyNKPgAAAAAAAACAAAAAAAAAAAAag0C8dXiHPQrXozwAAAAAAAAAgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAADqch09GWwarEMjSj4AAAAAAAAAgAAAAAAAAAAASY8AvoKKEb0K16M8AAAAAAAAAIAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlGgOSwRLE4aUaBJ0lFKUdS4=",
+        "achieved_goal": "[[ 0.0130892   0.08121299  0.02      ]\n [ 0.14785513 -0.12772149  0.02      ]\n [-0.01175001  0.06614772  0.02      ]\n [-0.12554659 -0.03553248  0.02      ]]",
+        "desired_goal": "[[ 0.05189816  0.12413325  0.04368898]\n [ 0.10917693  0.13059723  0.15760759]\n [-0.09292272  0.10585882  0.20478475]\n [ 0.04563163 -0.11165731  0.09937657]]",
+        "observation": "[[ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00  0.0000000e+00  1.3089203e-02\n   8.1212990e-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  1.4785513e-01\n  -1.2772149e-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]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00  0.0000000e+00 -1.1750007e-02\n   6.6147722e-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 -1.2554659e-01\n  -3.5532482e-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": 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:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 50,
+    "n_steps": 5,
+    "gamma": 0.99,
+    "gae_lambda": 1.0,
+    "ent_coef": 0.0,
+    "vf_coef": 0.5,
+    "max_grad_norm": 0.5,
+    "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:": "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"
+    }
+}

A2C-PandaPickAndPlaceDense-v3/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bda83e840cd93f804d541dcf5191f5c4a3b70941674028007ccab398a0ad7d5
+size 51951

A2C-PandaPickAndPlaceDense-v3/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:397512aba8bddbb173dac5da8736efea4efd2a9b4c0648cb6b4afb4ec35c3063
+size 53231

A2C-PandaPickAndPlaceDense-v3/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb4dde0c1ad63b7740276006a06cc491b21b407ea6c889928c223ec77ddad79f
+size 864

A2C-PandaPickAndPlaceDense-v3/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Windows-10-10.0.22631-SP0 10.0.22631
+- Python: 3.11.9
+- Stable-Baselines3: 2.0.0a5
+- PyTorch: 2.2.0
+- GPU Enabled: False
+- Numpy: 1.24.3
+- Cloudpickle: 3.0.0
+- Gymnasium: 0.28.1
+- OpenAI Gym: 0.26.2

README.md

@@ -0,0 +1,37 @@
+---
+library_name: stable-baselines3
+tags:
+- PandaPickAndPlaceDense-v3
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: A2C
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: PandaPickAndPlaceDense-v3
+      type: PandaPickAndPlaceDense-v3
+    metrics:
+    - type: mean_reward
+      value: -11.01 +/- 1.90
+      name: mean_reward
+      verified: false
+---
+
+# **A2C** Agent playing **PandaPickAndPlaceDense-v3**
+This is a trained model of a **A2C** agent playing **PandaPickAndPlaceDense-v3**
+using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
+
+## Usage (with Stable-baselines3)
+TODO: Add your code
+
+
+```python
+from stable_baselines3 import ...
+from huggingface_sb3 import load_from_hub
+
+...
+```

config.json

@@ -0,0 +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 0x0000021C7CE91620>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x0000021C7CE8A580>"}, "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": 1000, "_total_timesteps": 1000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1714989079990673900, "learning_rate": 0.0007, "tensorboard_log": null, "_last_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[ 1.3044112   0.7683268   0.12032255]\n [-0.66273177 -0.3659164   0.12032255]\n [ 0.6235068  -0.47585195  0.12032255]\n [-0.24543248  0.64232     0.12032255]]", "desired_goal": "[[ 1.8122001   1.5443218  -1.3811198 ]\n [ 0.879466    1.1630942   1.6339891 ]\n [-0.3728456  -1.1283029   1.804592  ]\n [-0.8088598  -0.37469706 -1.3811198 ]]", "observation": "[[ 0.5842109  -0.4916305   1.4156107   0.09762286 -0.02797361  0.11328804\n  -1.0602591   1.3044112   0.7683268   0.12032255 -0.03702876  0.2058336\n   0.03976776  0.14498791  0.08506173  0.07189737 -0.07872247 -0.00202583\n   0.08094105]\n [ 0.5842109  -0.4916305   1.4156107   0.09762286 -0.02797361  0.11328804\n  -1.0602591  -0.66273177 -0.3659164   0.12032255 -0.03702876  0.2058336\n   0.03976776  0.14498791  0.08506173  0.07189737 -0.07872247 -0.00202583\n   0.08094105]\n [ 0.5842109  -0.4916305   1.4156107   0.09762286 -0.02797361  0.11328804\n  -1.0602591   0.6235068  -0.47585195  0.12032255 -0.03702876  0.2058336\n   0.03976776  0.14498791  0.08506173  0.07189737 -0.07872247 -0.00202583\n   0.08094105]\n [ 0.5842109  -0.4916305   1.4156107   0.09762286 -0.02797361  0.11328804\n  -1.0602591  -0.24543248  0.64232     0.12032255 -0.03702876  0.2058336\n   0.03976776  0.14498791  0.08506173  0.07189737 -0.07872247 -0.00202583\n   0.08094105]]"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAEBAQGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[ 0.0130892   0.08121299  0.02      ]\n [ 0.14785513 -0.12772149  0.02      ]\n [-0.01175001  0.06614772  0.02      ]\n [-0.12554659 -0.03553248  0.02      ]]", "desired_goal": "[[ 0.05189816  0.12413325  0.04368898]\n [ 0.10917693  0.13059723  0.15760759]\n [-0.09292272  0.10585882  0.20478475]\n [ 0.04563163 -0.11165731  0.09937657]]", "observation": "[[ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00  0.0000000e+00  1.3089203e-02\n   8.1212990e-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  1.4785513e-01\n  -1.2772149e-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]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00  0.0000000e+00 -1.1750007e-02\n   6.6147722e-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 -1.2554659e-01\n  -3.5532482e-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": 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:": "gAWVgAIAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHwCBF0vGp++eMAWyUSzKMAXSURz/pImgJ1JUYdX2UKGgGR8Athb8FY+0PaAdLMmgIRz/mCoCMglnidX2UKGgGR8A0BZBsyi22aAdLMmgIRz/iR5kbxVhkdX2UKGgGR8AkWOdXko4NaAdLMmgIRz/eX05EMLF5dX2UKGgGR8AL49mpVCHAaAdLMmgIRz/zaKUFB6a9dX2UKGgGR8AVVD8cdYGMaAdLMmgIRz/x3LFGXokidX2UKGgGR8AgJA/s3Q2NaAdLMmgIRz/v9n003wTedX2UKGgGR8AojQBPsRg7aAdLMmgIRz/s3os7MgU2dX2UKGgGR8AmlhWHUMG5aAdLMmgIRz/6aaG5+YtydX2UKGgGR8A+PEZiuuA7aAdLMmgIRz/43a37UG3XdX2UKGgGR8AUK11GLDQ7aAdLMmgIRz/2/DtPYWcjdX2UKGgGR8Apl1ie/YapaAdLMmgIRz/1cEJSiudPdX2UKGgGR8AvEWgvlEJCaAdLMmgIR0AAucBltj0+dX2UKGgGR8AuFzbvgFX8aAdLMmgIRz//540Mw1zidX2UKGgGR8Aob6MR6F/QaAdLMmgIRz/+RhttQ9A5dX2UKGgGR8AmfcfNiYsvaAdLMmgIRz/8uiJwbVBldX2UKGgGR8AQwIcBEKE4aAdLMmgIR0AEkt29tdiVdX2UKGgGR8AM1MM7U5MlaAdLMmgIR0AD0NhE0BOpdX2UKGgGR8AlKH7gsK9gaAdLMmgIR0AC5Ea2nbZfdX2UKGgGR8AxPKekHlfaaAdLMmgIR0ACJkPMB6rvdWUu"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 50, "n_steps": 5, "gamma": 0.99, "gae_lambda": 1.0, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "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:": "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"}, "system_info": {"OS": "Windows-10-10.0.22631-SP0 10.0.22631", "Python": "3.11.9", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.2.0", "GPU Enabled": "False", "Numpy": "1.24.3", "Cloudpickle": "3.0.0", "Gymnasium": "0.28.1", "OpenAI Gym": "0.26.2"}}

results.json

@@ -0,0 +1 @@
+{"mean_reward": -11.008084380626679, "std_reward": 1.899477064985698, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-05-06T11:52:05.524857"}

vec_normalize.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8138ec3dd6cbea9eaee2e306e385262ad51316c49fd4cec8886f127ea799715
+size 2953