Upload PPO LunarLander-v2 trained agent
Browse files- README.md +1 -1
- config.json +1 -1
- ppo-LunarLander-v2.zip +2 -2
- ppo-LunarLander-v2/data +35 -23
- ppo-LunarLander-v2/policy.optimizer.pth +2 -2
- ppo-LunarLander-v2/policy.pth +2 -2
- 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: 315.81 +/- 9.19
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__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 0x7fdb1f821c20>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fdb1f821cb0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fdb1f821d40>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fdb1f821dd0>", "_build": "<function ActorCriticPolicy._build at 0x7fdb1f821e60>", "forward": "<function ActorCriticPolicy.forward at 0x7fdb1f821ef0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fdb1f821f80>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fdb1f824050>", "_predict": "<function ActorCriticPolicy._predict at 0x7fdb1f8240e0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fdb1f824170>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fdb1f824200>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fdb1f824290>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fdb1f86e930>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1179648, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1689102972495989708, "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:": "gASVmAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSxCFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDEAAAAAAAAAAAAAAAAAAAAACUdJRiLg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 0.410176, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 1120, "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:": "gASV9wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "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-5.15.90.1-microsoft-standard-WSL2-x86_64-with-debian-bookworm-sid # 1 SMP Fri Jan 27 02:56:13 UTC 2023", "Python": "3.7.16", "Stable-Baselines3": "2.0.0", "PyTorch": "1.13.1", "GPU Enabled": "True", "Numpy": "1.21.5", "Cloudpickle": "1.6.0", "Gymnasium": "0.28.1", "OpenAI Gym": "0.19.0"}}
|
|
|
1 |
+
{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__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 0x7f14a0463c20>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f14a0463cb0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f14a0463d40>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f14a0463dd0>", "_build": "<function ActorCriticPolicy._build at 0x7f14a0463e60>", "forward": "<function ActorCriticPolicy.forward at 0x7f14a0463ef0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f14a0463f80>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f14a0466050>", "_predict": "<function ActorCriticPolicy._predict at 0x7f14a04660e0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f14a0466170>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f14a0466200>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f14a0466290>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f14a04ad7e0>"}, "verbose": 1, "policy_kwargs": {"net_arch": {"pi": [128, 128], "vf": [128, 128, 128]}}, "num_timesteps": 786432, "_total_timesteps": 5000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1689119745303363630, "learning_rate": 3e-06, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gASVmAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSxCFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDEAAAAAAAAAAAAAAAAAAAAACUdJRiLg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 0.8427136, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 707, "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:": "gASV9wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "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-5.15.90.1-microsoft-standard-WSL2-x86_64-with-debian-bookworm-sid # 1 SMP Fri Jan 27 02:56:13 UTC 2023", "Python": "3.7.16", "Stable-Baselines3": "2.0.0", "PyTorch": "1.13.1", "GPU Enabled": "True", "Numpy": "1.21.5", "Cloudpickle": "1.6.0", "Gymnasium": "0.28.1", "OpenAI Gym": "0.19.0"}}
|
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 sha256:6afcae4b14e121dc6a300377638390ed6c8a3559f3cdec008f8883f779621a3f
|
3 |
+
size 661783
|
ppo-LunarLander-v2/data
CHANGED
@@ -4,34 +4,46 @@
|
|
4 |
":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
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_data object at
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
-
"policy_kwargs": {
|
24 |
-
|
25 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
-
"start_time":
|
30 |
-
"learning_rate":
|
31 |
"tensorboard_log": null,
|
32 |
"_last_obs": {
|
33 |
":type:": "<class 'numpy.ndarray'>",
|
34 |
-
":serialized:": "gASVjQIAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSxBLCIaUaAOMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////
|
35 |
},
|
36 |
"_last_episode_starts": {
|
37 |
":type:": "<class 'numpy.ndarray'>",
|
@@ -41,17 +53,17 @@
|
|
41 |
"_episode_num": 0,
|
42 |
"use_sde": false,
|
43 |
"sde_sample_freq": -1,
|
44 |
-
"_current_progress_remaining": 0.
|
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'>",
|
52 |
":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
53 |
},
|
54 |
-
"_n_updates":
|
55 |
"observation_space": {
|
56 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
57 |
":serialized:": "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",
|
@@ -94,6 +106,6 @@
|
|
94 |
"target_kl": null,
|
95 |
"lr_schedule": {
|
96 |
":type:": "<class 'function'>",
|
97 |
-
":serialized:": "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
|
98 |
}
|
99 |
}
|
|
|
4 |
":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
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 0x7f14a0463c20>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f14a0463cb0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f14a0463d40>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f14a0463dd0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f14a0463e60>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f14a0463ef0>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f14a0463f80>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f14a0466050>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f14a04660e0>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f14a0466170>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f14a0466200>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f14a0466290>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc_data object at 0x7f14a04ad7e0>"
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
+
"policy_kwargs": {
|
24 |
+
"net_arch": {
|
25 |
+
"pi": [
|
26 |
+
128,
|
27 |
+
128
|
28 |
+
],
|
29 |
+
"vf": [
|
30 |
+
128,
|
31 |
+
128,
|
32 |
+
128
|
33 |
+
]
|
34 |
+
}
|
35 |
+
},
|
36 |
+
"num_timesteps": 786432,
|
37 |
+
"_total_timesteps": 5000000,
|
38 |
"_num_timesteps_at_start": 0,
|
39 |
"seed": null,
|
40 |
"action_noise": null,
|
41 |
+
"start_time": 1689119745303363630,
|
42 |
+
"learning_rate": 3e-06,
|
43 |
"tensorboard_log": null,
|
44 |
"_last_obs": {
|
45 |
":type:": "<class 'numpy.ndarray'>",
|
46 |
+
":serialized:": "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"
|
47 |
},
|
48 |
"_last_episode_starts": {
|
49 |
":type:": "<class 'numpy.ndarray'>",
|
|
|
53 |
"_episode_num": 0,
|
54 |
"use_sde": false,
|
55 |
"sde_sample_freq": -1,
|
56 |
+
"_current_progress_remaining": 0.8427136,
|
57 |
"_stats_window_size": 100,
|
58 |
"ep_info_buffer": {
|
59 |
":type:": "<class 'collections.deque'>",
|
60 |
+
":serialized:": "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"
|
61 |
},
|
62 |
"ep_success_buffer": {
|
63 |
":type:": "<class 'collections.deque'>",
|
64 |
":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
65 |
},
|
66 |
+
"_n_updates": 707,
|
67 |
"observation_space": {
|
68 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
69 |
":serialized:": "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",
|
|
|
106 |
"target_kl": null,
|
107 |
"lr_schedule": {
|
108 |
":type:": "<class 'function'>",
|
109 |
+
":serialized:": "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"
|
110 |
}
|
111 |
}
|
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bfaa9781f3e127ea48e97092ff4847487f218cfef71608258157be9c18fd13ae
|
3 |
+
size 431207
|
ppo-LunarLander-v2/policy.pth
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:bae983f13fbbcb325fdfa781af1d63d1da80f3c971dd4dc9e5c817f696367934
|
3 |
+
size 214715
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 315.8127915208895, "std_reward": 9.187895669341543, "is_deterministic": true, "n_eval_episodes": 2, "eval_datetime": "2023-07-12T03:14:12.275961"}
|