RadG commited on
Commit
48afbb7
1 Parent(s): 592db84

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: -454.72 +/- 151.51
20
  name: mean_reward
21
  verified: false
22
  ---
 
16
  type: LunarLander-v2
17
  metrics:
18
  - type: mean_reward
19
+ value: 238.26 +/- 51.54
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 0x7a4a6b8d2cb0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7a4a6b8d2d40>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7a4a6b8d2dd0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7a4a6b8d2e60>", "_build": "<function ActorCriticPolicy._build at 0x7a4a6b8d2ef0>", "forward": "<function ActorCriticPolicy.forward at 0x7a4a6b8d2f80>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7a4a6b8d3010>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7a4a6b8d30a0>", "_predict": "<function ActorCriticPolicy._predict at 0x7a4a6b8d3130>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7a4a6b8d31c0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7a4a6b8d3250>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7a4a6b8d32e0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7a4a6ba6e840>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 16384, "_total_timesteps": 10000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1709794308806100390, "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:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAQAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.6384000000000001, "_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": 4, "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": 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-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 0x793264df9900>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x793264df9990>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x793264df9a20>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x793264df9ab0>", "_build": "<function ActorCriticPolicy._build at 0x793264df9b40>", "forward": "<function ActorCriticPolicy.forward at 0x793264df9bd0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x793264df9c60>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x793264df9cf0>", "_predict": "<function ActorCriticPolicy._predict at 0x793264df9d80>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x793264df9e10>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x793264df9ea0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x793264df9f30>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x793264f91780>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1709880242328003259, "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:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "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-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 sha256:455cf4ced980df577a475d1e0f9516fde689b628b4486bdeb4dbae5c74158fcc
3
- size 147944
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13eb5194e76f2cdc6d81a2aace95c23194dda3f32f75c796bb789a9c3cedb280
3
+ size 148080
ppo-LunarLander-v2/data CHANGED
@@ -4,54 +4,54 @@
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 0x7a4a6b8d2cb0>",
8
- "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7a4a6b8d2d40>",
9
- "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7a4a6b8d2dd0>",
10
- "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7a4a6b8d2e60>",
11
- "_build": "<function ActorCriticPolicy._build at 0x7a4a6b8d2ef0>",
12
- "forward": "<function ActorCriticPolicy.forward at 0x7a4a6b8d2f80>",
13
- "extract_features": "<function ActorCriticPolicy.extract_features at 0x7a4a6b8d3010>",
14
- "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7a4a6b8d30a0>",
15
- "_predict": "<function ActorCriticPolicy._predict at 0x7a4a6b8d3130>",
16
- "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7a4a6b8d31c0>",
17
- "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7a4a6b8d3250>",
18
- "predict_values": "<function ActorCriticPolicy.predict_values at 0x7a4a6b8d32e0>",
19
  "__abstractmethods__": "frozenset()",
20
- "_abc_impl": "<_abc._abc_data object at 0x7a4a6ba6e840>"
21
  },
22
  "verbose": 1,
23
  "policy_kwargs": {},
24
- "num_timesteps": 16384,
25
- "_total_timesteps": 10000,
26
  "_num_timesteps_at_start": 0,
27
  "seed": null,
28
  "action_noise": null,
29
- "start_time": 1709794308806100390,
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'>",
38
- ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAQAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
39
  },
40
  "_last_original_obs": null,
41
  "_episode_num": 0,
42
  "use_sde": false,
43
  "sde_sample_freq": -1,
44
- "_current_progress_remaining": -0.6384000000000001,
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": 4,
55
  "observation_space": {
56
  ":type:": "<class 'gymnasium.spaces.box.Box'>",
57
  ":serialized:": "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",
 
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 0x793264df9900>",
8
+ "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x793264df9990>",
9
+ "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x793264df9a20>",
10
+ "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x793264df9ab0>",
11
+ "_build": "<function ActorCriticPolicy._build at 0x793264df9b40>",
12
+ "forward": "<function ActorCriticPolicy.forward at 0x793264df9bd0>",
13
+ "extract_features": "<function ActorCriticPolicy.extract_features at 0x793264df9c60>",
14
+ "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x793264df9cf0>",
15
+ "_predict": "<function ActorCriticPolicy._predict at 0x793264df9d80>",
16
+ "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x793264df9e10>",
17
+ "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x793264df9ea0>",
18
+ "predict_values": "<function ActorCriticPolicy.predict_values at 0x793264df9f30>",
19
  "__abstractmethods__": "frozenset()",
20
+ "_abc_impl": "<_abc._abc_data object at 0x793264f91780>"
21
  },
22
  "verbose": 1,
23
  "policy_kwargs": {},
24
+ "num_timesteps": 1015808,
25
+ "_total_timesteps": 1000000,
26
  "_num_timesteps_at_start": 0,
27
  "seed": null,
28
  "action_noise": null,
29
+ "start_time": 1709880242328003259,
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'>",
38
+ ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
39
  },
40
  "_last_original_obs": null,
41
  "_episode_num": 0,
42
  "use_sde": false,
43
  "sde_sample_freq": -1,
44
+ "_current_progress_remaining": -0.015808000000000044,
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": 248,
55
  "observation_space": {
56
  ":type:": "<class 'gymnasium.spaces.box.Box'>",
57
  ":serialized:": "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",
ppo-LunarLander-v2/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f18d99a220f24063ebe73a68874b3ba4bdc09087fb7b0ca4b53bfa517d52189
3
  size 88362
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:702b3e29a31c9cc83121d9d6fc479236487c6c6b030edfc7070a9f94ddf6b362
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:f9aa7afc690eb5fbfb886b0c7fbc95926aba1a198adf83cfd5caa4085903451f
3
  size 43762
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d0be9e38add1aaaa66b9c7ee15716b84ae546176dab3ea21c55d9d5da8190fd
3
  size 43762
replay.mp4 CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
 
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": -454.7180334915465, "std_reward": 151.5098408727235, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-07T06:56:00.993037"}
 
1
+ {"mean_reward": 238.25927951615208, "std_reward": 51.53579354540695, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-08T07:19:08.627375"}