michael-kingston
commited on
Commit
•
6b67800
1
Parent(s):
ed09719
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 +17 -17
- ppo-LunarLander-v2/policy.optimizer.pth +1 -1
- ppo-LunarLander-v2/policy.pth +1 -1
- replay.mp4 +0 -0
- results.json +1 -1
README.md
CHANGED
@@ -16,7 +16,7 @@ model-index:
|
|
16 |
type: LunarLander-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
-
value:
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
|
|
16 |
type: LunarLander-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
+
value: 280.04 +/- 17.38
|
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 0x7f228fb2fe20>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f228fb2feb0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f228fb2ff40>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f228fb48040>", "_build": "<function ActorCriticPolicy._build at 0x7f228fb480d0>", "forward": "<function ActorCriticPolicy.forward at 0x7f228fb48160>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f228fb481f0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f228fb48280>", "_predict": "<function ActorCriticPolicy._predict at 0x7f228fb48310>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f228fb483a0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f228fb48430>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f228fb484c0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f228fb443c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 0, "_total_timesteps": 10000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1698207138287156101, "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:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAEBAQEBAQEBAQEBAQEBAQGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 1.0, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 0, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "gAWVcAIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoB4wCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoECiWCAAAAAAAAAABAQEBAQEBAZRoFEsIhZRoGHSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBAoliAAAAAAAAAAAAC0wgAAtMIAAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaApLCIWUaBh0lFKUjARoaWdolGgQKJYgAAAAAAAAAAAAtEIAALRCAACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgKSwiFlGgYdJRSlIwIbG93X3JlcHKUjFtbLTkwLiAgICAgICAgLTkwLiAgICAgICAgIC01LiAgICAgICAgIC01LiAgICAgICAgIC0zLjE0MTU5MjcgIC01LgogIC0wLiAgICAgICAgIC0wLiAgICAgICBdlIwJaGlnaF9yZXBylIxTWzkwLiAgICAgICAgOTAuICAgICAgICAgNS4gICAgICAgICA1LiAgICAgICAgIDMuMTQxNTkyNyAgNS4KICAxLiAgICAgICAgIDEuICAgICAgIF2UjApfbnBfcmFuZG9tlE51Yi4=", "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": 2048, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 10240, "n_epochs": 5, "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-6.5.6-76060506-generic-x86_64-with-glibc2.35 # 202310061235~1697396945~22.04~9283e32 SMP PREEMPT_DYNAMIC Sun O", "Python": "3.10.12", "Stable-Baselines3": "2.1.0", "PyTorch": "2.1.0", "GPU Enabled": "True", "Numpy": "1.22.4", "Cloudpickle": "3.0.0", "Gymnasium": "0.28.1"}}
|
|
|
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 0x7cb1e7eb0670>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7cb1e7eb0700>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7cb1e7eb0790>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7cb1e7eb0820>", "_build": "<function ActorCriticPolicy._build at 0x7cb1e7eb08b0>", "forward": "<function ActorCriticPolicy.forward at 0x7cb1e7eb0940>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7cb1e7eb09d0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7cb1e7eb0a60>", "_predict": "<function ActorCriticPolicy._predict at 0x7cb1e7eb0af0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7cb1e7eb0b80>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7cb1e7eb0c10>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7cb1e7eb0ca0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7cb1e7ea9480>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1698211267408405571, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.015808000000000044, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 248, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True True True True True True True True]", "bounded_above": "[ True True True True True True True True]", "_shape": [8], "low": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.1.0+cu118", "GPU Enabled": "True", "Numpy": "1.23.5", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
|
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 sha256:27a28e95c07fcb87f91f6422b98fa773deffe138ea3ce4f8753748bb229cc4eb
|
3 |
+
size 148010
|
ppo-LunarLander-v2/data
CHANGED
@@ -4,20 +4,20 @@
|
|
4 |
":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
5 |
"__module__": "stable_baselines3.common.policies",
|
6 |
"__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ",
|
7 |
-
"__init__": "<function ActorCriticPolicy.__init__ at
|
8 |
-
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at
|
9 |
-
"reset_noise": "<function ActorCriticPolicy.reset_noise at
|
10 |
-
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at
|
11 |
-
"_build": "<function ActorCriticPolicy._build at
|
12 |
-
"forward": "<function ActorCriticPolicy.forward at
|
13 |
-
"extract_features": "<function ActorCriticPolicy.extract_features at
|
14 |
-
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at
|
15 |
-
"_predict": "<function ActorCriticPolicy._predict at
|
16 |
-
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at
|
17 |
-
"get_distribution": "<function ActorCriticPolicy.get_distribution at
|
18 |
-
"predict_values": "<function ActorCriticPolicy.predict_values at
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
-
"_abc_impl": "<_abc._abc_data object at
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
@@ -26,12 +26,12 @@
|
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
-
"start_time":
|
30 |
"learning_rate": 0.0003,
|
31 |
"tensorboard_log": null,
|
32 |
"_last_obs": {
|
33 |
":type:": "<class 'numpy.ndarray'>",
|
34 |
-
":serialized:": "
|
35 |
},
|
36 |
"_last_episode_starts": {
|
37 |
":type:": "<class 'numpy.ndarray'>",
|
@@ -45,7 +45,7 @@
|
|
45 |
"_stats_window_size": 100,
|
46 |
"ep_info_buffer": {
|
47 |
":type:": "<class 'collections.deque'>",
|
48 |
-
":serialized:": "
|
49 |
},
|
50 |
"ep_success_buffer": {
|
51 |
":type:": "<class 'collections.deque'>",
|
@@ -83,7 +83,7 @@
|
|
83 |
"ent_coef": 0.01,
|
84 |
"vf_coef": 0.5,
|
85 |
"max_grad_norm": 0.5,
|
86 |
-
"batch_size":
|
87 |
"n_epochs": 4,
|
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 0x7cb1e7eb0670>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7cb1e7eb0700>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7cb1e7eb0790>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7cb1e7eb0820>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7cb1e7eb08b0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7cb1e7eb0940>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7cb1e7eb09d0>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7cb1e7eb0a60>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7cb1e7eb0af0>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7cb1e7eb0b80>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7cb1e7eb0c10>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7cb1e7eb0ca0>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7cb1e7ea9480>"
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
|
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
+
"start_time": 1698211267408405571,
|
30 |
"learning_rate": 0.0003,
|
31 |
"tensorboard_log": null,
|
32 |
"_last_obs": {
|
33 |
":type:": "<class 'numpy.ndarray'>",
|
34 |
+
":serialized:": "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"
|
35 |
},
|
36 |
"_last_episode_starts": {
|
37 |
":type:": "<class 'numpy.ndarray'>",
|
|
|
45 |
"_stats_window_size": 100,
|
46 |
"ep_info_buffer": {
|
47 |
":type:": "<class 'collections.deque'>",
|
48 |
+
":serialized:": "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"
|
49 |
},
|
50 |
"ep_success_buffer": {
|
51 |
":type:": "<class 'collections.deque'>",
|
|
|
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'>",
|
ppo-LunarLander-v2/policy.optimizer.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 88362
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e7c8e60df3407f375c510470f8eb666160bd670c3caf68cc5f8de7ac3f1860d7
|
3 |
size 88362
|
ppo-LunarLander-v2/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 43762
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1913ab1700180ca890a8d3988fba25268d29729b0ea17b18f38e94d9206ce1d4
|
3 |
size 43762
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 280.04105, "std_reward": 17.38200150831363, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-10-25T05:40:42.518363"}
|