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 +23 -23
- ppo-LunarLander-v2/policy.optimizer.pth +1 -1
- ppo-LunarLander-v2/policy.pth +1 -1
- replay.mp4 +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: 273.76 +/- 24.46
|
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 0x7f842d8c85e0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f842d8c8670>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f842d8c8700>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f842d8c8790>", "_build": "<function ActorCriticPolicy._build at 0x7f842d8c8820>", "forward": "<function ActorCriticPolicy.forward at 0x7f842d8c88b0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f842d8c8940>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f842d8c89d0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f842d8c8a60>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f842d8c8af0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f842d8c8b80>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f842d8c8c10>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f842d8bd700>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1212416, "_total_timesteps": 1200000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1687003316420763614, "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": -0.010346666666666726, "_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": 592, "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": 0.998, "gae_lambda": 0.98, "ent_coef": 0.005, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 32, "n_epochs": 8, "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-5.15.107+-x86_64-with-glibc2.31 # 1 SMP Sat Apr 29 09:15:28 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "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 0x7f3d78069090>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f3d78069120>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f3d780691b0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f3d78069240>", "_build": "<function ActorCriticPolicy._build at 0x7f3d780692d0>", "forward": "<function ActorCriticPolicy.forward at 0x7f3d78069360>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f3d780693f0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f3d78069480>", "_predict": "<function ActorCriticPolicy._predict at 0x7f3d78069510>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f3d780695a0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f3d78069630>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f3d780696c0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f3d78057fc0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1507328, "_total_timesteps": 1500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1687154919450622070, "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": -0.004885333333333408, "_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": 736, "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": 0.995, "gae_lambda": 0.995, "ent_coef": 0.005, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 8, "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-5.15.107+-x86_64-with-glibc2.31 # 1 SMP Sat Apr 29 09:15:28 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "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 sha256:2231f58be004741a328d48b787b8c550460c47a6c6ec9151ae28a63f20bc88e2
|
3 |
+
size 146629
|
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
|
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": {},
|
24 |
-
"num_timesteps":
|
25 |
-
"_total_timesteps":
|
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'>",
|
@@ -41,17 +41,17 @@
|
|
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:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
53 |
},
|
54 |
-
"_n_updates":
|
55 |
"observation_space": {
|
56 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
57 |
":serialized:": "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",
|
@@ -78,12 +78,12 @@
|
|
78 |
},
|
79 |
"n_envs": 16,
|
80 |
"n_steps": 1024,
|
81 |
-
"gamma": 0.
|
82 |
-
"gae_lambda": 0.
|
83 |
"ent_coef": 0.005,
|
84 |
"vf_coef": 0.5,
|
85 |
"max_grad_norm": 0.5,
|
86 |
-
"batch_size":
|
87 |
"n_epochs": 8,
|
88 |
"clip_range": {
|
89 |
":type:": "<class 'function'>",
|
|
|
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 0x7f3d78069090>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f3d78069120>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f3d780691b0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f3d78069240>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f3d780692d0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f3d78069360>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f3d780693f0>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f3d78069480>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f3d78069510>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f3d780695a0>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f3d78069630>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f3d780696c0>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7f3d78057fc0>"
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
24 |
+
"num_timesteps": 1507328,
|
25 |
+
"_total_timesteps": 1500000,
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
+
"start_time": 1687154919450622070,
|
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'>",
|
|
|
41 |
"_episode_num": 0,
|
42 |
"use_sde": false,
|
43 |
"sde_sample_freq": -1,
|
44 |
+
"_current_progress_remaining": -0.004885333333333408,
|
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": 736,
|
55 |
"observation_space": {
|
56 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
57 |
":serialized:": "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",
|
|
|
78 |
},
|
79 |
"n_envs": 16,
|
80 |
"n_steps": 1024,
|
81 |
+
"gamma": 0.995,
|
82 |
+
"gae_lambda": 0.995,
|
83 |
"ent_coef": 0.005,
|
84 |
"vf_coef": 0.5,
|
85 |
"max_grad_norm": 0.5,
|
86 |
+
"batch_size": 64,
|
87 |
"n_epochs": 8,
|
88 |
"clip_range": {
|
89 |
":type:": "<class 'function'>",
|
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 87929
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:defd0a84501c3854b610b2cb83105fafa5dc1724997f622590b6b0d0022f90f9
|
3 |
size 87929
|
ppo-LunarLander-v2/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 43329
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff0277c7b57e82bf59124f5f2529961929c3e81c11eab0e19ec0d14f887fdea6
|
3 |
size 43329
|
replay.mp4
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 sha256:6e88b66f7250de59d5b3f2239af23bc977cea70614985e50dec423db4308f548
|
3 |
+
size 188720
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 273.7610188, "std_reward": 24.463119184028276, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-06-19T06:56:07.942163"}
|