Upload PPO LunarLander-v2 trained agent with Optuna HP search
Browse files- README.md +1 -1
- config.json +1 -1
- ppo-LunarLander-v2.zip +2 -2
- ppo-LunarLander-v2/data +16 -16
- ppo-LunarLander-v2/policy.optimizer.pth +1 -1
- ppo-LunarLander-v2/policy.pth +1 -1
- replay.mp4 +0 -0
- results.json +1 -1
README.md
CHANGED
@@ -16,7 +16,7 @@ model-index:
|
|
16 |
type: LunarLander-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
-
value:
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
|
|
16 |
type: LunarLander-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
+
value: 261.77 +/- 22.97
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n 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\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: Features extractor to use.\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 ActorCriticPolicy.__init__ at 0x792a052da440>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x792a052da4d0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x792a052da560>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x792a052da5f0>", "_build": "<function ActorCriticPolicy._build at 0x792a052da680>", "forward": "<function ActorCriticPolicy.forward at 0x792a052da710>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x792a052da7a0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x792a052da830>", "_predict": "<function ActorCriticPolicy._predict at 0x792a052da8c0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x792a052da950>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x792a052da9e0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x792a052daa70>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x792a052dc940>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1699949349674283890, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.015808000000000044, "_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": 248, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True True True True True True True True]", "bounded_above": "[ True True True True True True True True]", "_shape": [8], "low": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.1.0+cu118", "GPU Enabled": "True", "Numpy": "1.23.5", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
|
|
|
1 |
+
{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n 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\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: Features extractor to use.\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 ActorCriticPolicy.__init__ at 0x7e805d3acd30>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7e805d3acdc0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7e805d3ace50>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7e805d3acee0>", "_build": "<function ActorCriticPolicy._build at 0x7e805d3acf70>", "forward": "<function ActorCriticPolicy.forward at 0x7e805d3ad000>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7e805d3ad090>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7e805d3ad120>", "_predict": "<function ActorCriticPolicy._predict at 0x7e805d3ad1b0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7e805d3ad240>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7e805d3ad2d0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7e805d3ad360>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7e805d3a4c80>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1701348739130300536, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.015808000000000044, "_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": 248, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True True True True True True True True]", "bounded_above": "[ True True True True True True True True]", "_shape": [8], "low": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "system_info": {"OS": "Linux-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.1.0+cu118", "GPU Enabled": "True", "Numpy": "1.23.5", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
|
ppo-LunarLander-v2.zip
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0174fd05b03361b7d4f4885d8e509abb95a26aeeb42750a9e4a825f7c66bbc3d
|
3 |
+
size 148030
|
ppo-LunarLander-v2/data
CHANGED
@@ -4,20 +4,20 @@
|
|
4 |
":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
5 |
"__module__": "stable_baselines3.common.policies",
|
6 |
"__doc__": "\n 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\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: Features extractor to use.\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 ",
|
7 |
-
"__init__": "<function ActorCriticPolicy.__init__ at
|
8 |
-
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at
|
9 |
-
"reset_noise": "<function ActorCriticPolicy.reset_noise at
|
10 |
-
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at
|
11 |
-
"_build": "<function ActorCriticPolicy._build at
|
12 |
-
"forward": "<function ActorCriticPolicy.forward at
|
13 |
-
"extract_features": "<function ActorCriticPolicy.extract_features at
|
14 |
-
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at
|
15 |
-
"_predict": "<function ActorCriticPolicy._predict at
|
16 |
-
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at
|
17 |
-
"get_distribution": "<function ActorCriticPolicy.get_distribution at
|
18 |
-
"predict_values": "<function ActorCriticPolicy.predict_values at
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
-
"_abc_impl": "<_abc._abc_data object at
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
@@ -26,12 +26,12 @@
|
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
-
"start_time":
|
30 |
"learning_rate": 0.0003,
|
31 |
"tensorboard_log": null,
|
32 |
"_last_obs": {
|
33 |
":type:": "<class 'numpy.ndarray'>",
|
34 |
-
":serialized:": "
|
35 |
},
|
36 |
"_last_episode_starts": {
|
37 |
":type:": "<class 'numpy.ndarray'>",
|
@@ -45,7 +45,7 @@
|
|
45 |
"_stats_window_size": 100,
|
46 |
"ep_info_buffer": {
|
47 |
":type:": "<class 'collections.deque'>",
|
48 |
-
":serialized:": "
|
49 |
},
|
50 |
"ep_success_buffer": {
|
51 |
":type:": "<class 'collections.deque'>",
|
|
|
4 |
":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
5 |
"__module__": "stable_baselines3.common.policies",
|
6 |
"__doc__": "\n 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\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: Features extractor to use.\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 ",
|
7 |
+
"__init__": "<function ActorCriticPolicy.__init__ at 0x7e805d3acd30>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7e805d3acdc0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7e805d3ace50>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7e805d3acee0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7e805d3acf70>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7e805d3ad000>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7e805d3ad090>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7e805d3ad120>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7e805d3ad1b0>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7e805d3ad240>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7e805d3ad2d0>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7e805d3ad360>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7e805d3a4c80>"
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
|
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
+
"start_time": 1701348739130300536,
|
30 |
"learning_rate": 0.0003,
|
31 |
"tensorboard_log": null,
|
32 |
"_last_obs": {
|
33 |
":type:": "<class 'numpy.ndarray'>",
|
34 |
+
":serialized:": "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"
|
35 |
},
|
36 |
"_last_episode_starts": {
|
37 |
":type:": "<class 'numpy.ndarray'>",
|
|
|
45 |
"_stats_window_size": 100,
|
46 |
"ep_info_buffer": {
|
47 |
":type:": "<class 'collections.deque'>",
|
48 |
+
":serialized:": "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"
|
49 |
},
|
50 |
"ep_success_buffer": {
|
51 |
":type:": "<class 'collections.deque'>",
|
ppo-LunarLander-v2/policy.optimizer.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 88362
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f252bf671dd2a19bc7d5c2b227ef93b4251d6d7efffe0d71163dfeb73450fada
|
3 |
size 88362
|
ppo-LunarLander-v2/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 43762
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:20c60ac2215be58b7be0faeba3589a737c755ea3223f41d98b875e18ce5459ba
|
3 |
size 43762
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 261.76644, "std_reward": 22.97423246104001, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-11-30T13:13:00.710265"}
|