YusufTree commited on
Commit
85c80d7
1 Parent(s): c469000

Upload PPO LunarLander-v2 trained agent

Browse files
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: LunarLander-v2
17
  metrics:
18
  - type: mean_reward
19
- value: 213.69 +/- 76.42
20
  name: mean_reward
21
  verified: false
22
  ---
 
16
  type: LunarLander-v2
17
  metrics:
18
  - type: mean_reward
19
+ value: -1402.61 +/- 257.49
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 0x7ed824144b80>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ed824144c10>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ed824144ca0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ed824144d30>", "_build": "<function ActorCriticPolicy._build at 0x7ed824144dc0>", "forward": "<function ActorCriticPolicy.forward at 0x7ed824144e50>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ed824144ee0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ed824144f70>", "_predict": "<function ActorCriticPolicy._predict at 0x7ed824145000>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ed824145090>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ed824145120>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ed8241451b0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7ed8242d6f80>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1000448, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1708708180253058445, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAADPkAj1mDQ8/UoeIvWd0GL6WEPC8+jatvQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.00044800000000000395, "_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": 3908, "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:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "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-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": "2.0.0a5", "PyTorch": "2.1.0+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "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 0x7c9725ee09d0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7c9725ee0a60>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7c9725ee0af0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7c9725ee0b80>", "_build": "<function ActorCriticPolicy._build at 0x7c9725ee0c10>", "forward": "<function ActorCriticPolicy.forward at 0x7c9725ee0ca0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7c9725ee0d30>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7c9725ee0dc0>", "_predict": "<function ActorCriticPolicy._predict at 0x7c9725ee0e50>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7c9725ee0ee0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7c9725ee0f70>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7c9725ee1000>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7c9725e7cf40>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 2000896, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1709565032532411298, "learning_rate": 1e-05, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAKX9zr7xJl8+Dpo3vhljq7+IMI2/aP+evgAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.00044800000000000395, "_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": 7816, "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:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "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": 512, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "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": "2.0.0a5", "PyTorch": "2.1.0+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "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 sha256:5bb66ffb800773d262ce17cdd2e0d2fb178c684d2d1ef3f0a7e74aeb2644ce28
3
- size 147426
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c8bb944ee3c399314244c78914e9d6e8e455a768326dce270c6f9c14b3f47d2
3
+ size 147298
ppo-LunarLander-v2/data CHANGED
@@ -4,34 +4,34 @@
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 0x7ed824144b80>",
8
- "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ed824144c10>",
9
- "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ed824144ca0>",
10
- "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ed824144d30>",
11
- "_build": "<function ActorCriticPolicy._build at 0x7ed824144dc0>",
12
- "forward": "<function ActorCriticPolicy.forward at 0x7ed824144e50>",
13
- "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ed824144ee0>",
14
- "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ed824144f70>",
15
- "_predict": "<function ActorCriticPolicy._predict at 0x7ed824145000>",
16
- "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ed824145090>",
17
- "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ed824145120>",
18
- "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ed8241451b0>",
19
  "__abstractmethods__": "frozenset()",
20
- "_abc_impl": "<_abc._abc_data object at 0x7ed8242d6f80>"
21
  },
22
  "verbose": 1,
23
  "policy_kwargs": {},
24
- "num_timesteps": 1000448,
25
- "_total_timesteps": 1000000,
26
  "_num_timesteps_at_start": 0,
27
  "seed": null,
28
  "action_noise": null,
29
- "start_time": 1708708180253058445,
30
- "learning_rate": 0.0003,
31
  "tensorboard_log": null,
32
  "_last_obs": {
33
  ":type:": "<class 'numpy.ndarray'>",
34
- ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAADPkAj1mDQ8/UoeIvWd0GL6WEPC8+jatvQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
35
  },
36
  "_last_episode_starts": {
37
  ":type:": "<class 'numpy.ndarray'>",
@@ -45,13 +45,13 @@
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'>",
52
  ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
53
  },
54
- "_n_updates": 3908,
55
  "observation_space": {
56
  ":type:": "<class 'gymnasium.spaces.box.Box'>",
57
  ":serialized:": "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",
@@ -83,7 +83,7 @@
83
  "ent_coef": 0.01,
84
  "vf_coef": 0.5,
85
  "max_grad_norm": 0.5,
86
- "batch_size": 64,
87
  "n_epochs": 4,
88
  "clip_range": {
89
  ":type:": "<class 'function'>",
@@ -94,6 +94,6 @@
94
  "target_kl": null,
95
  "lr_schedule": {
96
  ":type:": "<class 'function'>",
97
- ":serialized:": "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"
98
  }
99
  }
 
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 0x7c9725ee09d0>",
8
+ "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7c9725ee0a60>",
9
+ "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7c9725ee0af0>",
10
+ "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7c9725ee0b80>",
11
+ "_build": "<function ActorCriticPolicy._build at 0x7c9725ee0c10>",
12
+ "forward": "<function ActorCriticPolicy.forward at 0x7c9725ee0ca0>",
13
+ "extract_features": "<function ActorCriticPolicy.extract_features at 0x7c9725ee0d30>",
14
+ "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7c9725ee0dc0>",
15
+ "_predict": "<function ActorCriticPolicy._predict at 0x7c9725ee0e50>",
16
+ "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7c9725ee0ee0>",
17
+ "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7c9725ee0f70>",
18
+ "predict_values": "<function ActorCriticPolicy.predict_values at 0x7c9725ee1000>",
19
  "__abstractmethods__": "frozenset()",
20
+ "_abc_impl": "<_abc._abc_data object at 0x7c9725e7cf40>"
21
  },
22
  "verbose": 1,
23
  "policy_kwargs": {},
24
+ "num_timesteps": 2000896,
25
+ "_total_timesteps": 2000000,
26
  "_num_timesteps_at_start": 0,
27
  "seed": null,
28
  "action_noise": null,
29
+ "start_time": 1709565032532411298,
30
+ "learning_rate": 1e-05,
31
  "tensorboard_log": null,
32
  "_last_obs": {
33
  ":type:": "<class 'numpy.ndarray'>",
34
+ ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAKX9zr7xJl8+Dpo3vhljq7+IMI2/aP+evgAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
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'>",
52
  ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
53
  },
54
+ "_n_updates": 7816,
55
  "observation_space": {
56
  ":type:": "<class 'gymnasium.spaces.box.Box'>",
57
  ":serialized:": "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",
 
83
  "ent_coef": 0.01,
84
  "vf_coef": 0.5,
85
  "max_grad_norm": 0.5,
86
+ "batch_size": 512,
87
  "n_epochs": 4,
88
  "clip_range": {
89
  ":type:": "<class 'function'>",
 
94
  "target_kl": null,
95
  "lr_schedule": {
96
  ":type:": "<class 'function'>",
97
+ ":serialized:": "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"
98
  }
99
  }
ppo-LunarLander-v2/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d9a0db6cdf193d685c3a717a8d4eb959110ca68f03866e7122571bf1f3fc61e
3
  size 88362
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e87af1616e73f72aca722fa93f9b07163b2833cf90f620db2f3d4beb100943cf
3
  size 88362
ppo-LunarLander-v2/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5d448ad12fe00432dca20d58a135d8e577a5eddc9fda53ee4e86801b41a44bcc
3
  size 43762
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf831eb6b3ef7bb1aa0389976347f82bb906aa1b876b213dc3fe040d069d18b8
3
  size 43762
replay.mp4 CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
 
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 213.68540789999997, "std_reward": 76.42248762301782, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-02-23T17:53:39.558235"}
 
1
+ {"mean_reward": -1402.6076093, "std_reward": 257.4918642655671, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-04T16:03:12.052103"}