micheljperez
commited on
Commit
•
bdad849
1
Parent(s):
f9ed28d
Initial 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 +16 -16
- ppo-LunarLander-v2/policy.optimizer.pth +1 -1
- ppo-LunarLander-v2/policy.pth +1 -1
- 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: 243.37 +/- 83.64
|
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 0x142a4c9d0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x142a4ca60>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x142a4caf0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x142a4cb80>", "_build": "<function ActorCriticPolicy._build at 0x142a4cc10>", "forward": "<function ActorCriticPolicy.forward at 0x142a4cca0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x142a4cd30>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x142a4cdc0>", "_predict": "<function ActorCriticPolicy._predict at 0x142a4ce50>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x142a4cee0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x142a4cf70>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x142a56040>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x142a53180>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 40000512, "_total_timesteps": 40000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1696946547316991000, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAJppQLu2/eU+eD3VPHvW6r7SNDY9F1cxPQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -1.2799999999923983e-05, "_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": 156252, "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": 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": "macOS-13.6-arm64-arm-64bit Darwin Kernel Version 22.6.0: Fri Sep 15 13:41:28 PDT 2023; root:xnu-8796.141.3.700.8~1/RELEASE_ARM64_T6000", "Python": "3.8.10", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.1.0", "GPU Enabled": "False", "Numpy": "1.24.4", "Cloudpickle": "2.2.1", "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 0x1436d29d0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x1436d2a60>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x1436d2af0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x1436d2b80>", "_build": "<function ActorCriticPolicy._build at 0x1436d2c10>", "forward": "<function ActorCriticPolicy.forward at 0x1436d2ca0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x1436d2d30>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x1436d2dc0>", "_predict": "<function ActorCriticPolicy._predict at 0x1436d2e50>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x1436d2ee0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x1436d2f70>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x1436d7040>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x1436d4210>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 40000512, "_total_timesteps": 40000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1697462409429829000, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAADgpLq0Zm8+Zncovkdn+b7APkG9KsmwvQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -1.2799999999923983e-05, "_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": 156252, "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": 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:": "gAWVEQMAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMby9MaWJyYXJ5L0ZyYW1ld29ya3MvUHl0aG9uLmZyYW1ld29yay9WZXJzaW9ucy8zLjgvbGliL3B5dGhvbjMuOC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4RDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMby9MaWJyYXJ5L0ZyYW1ld29ya3MvUHl0aG9uLmZyYW1ld29yay9WZXJzaW9ucy8zLjgvbGliL3B5dGhvbjMuOC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/M6kqMFUyYYWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="}, "system_info": {"OS": "macOS-13.6-arm64-arm-64bit Darwin Kernel Version 22.6.0: Fri Sep 15 13:41:28 PDT 2023; root:xnu-8796.141.3.700.8~1/RELEASE_ARM64_T6000", "Python": "3.8.10", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.1.0", "GPU Enabled": "False", "Numpy": "1.24.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1"}}
|
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 sha256:6650959345faea4ba4c6396392e9528a5a1ad0717640d4aa83b1d5b20bb4e14b
|
3 |
+
size 147037
|
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_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'>",
|
|
|
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 0x1436d29d0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x1436d2a60>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x1436d2af0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x1436d2b80>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x1436d2c10>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x1436d2ca0>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x1436d2d30>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x1436d2dc0>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x1436d2e50>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x1436d2ee0>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x1436d2f70>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x1436d7040>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc_data object at 0x1436d4210>"
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
|
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
+
"start_time": 1697462409429829000,
|
30 |
"learning_rate": 0.0003,
|
31 |
"tensorboard_log": null,
|
32 |
"_last_obs": {
|
33 |
":type:": "<class 'numpy.ndarray'>",
|
34 |
+
":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAADgpLq0Zm8+Zncovkdn+b7APkG9KsmwvQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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'>",
|
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 88042
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:28ebab00ea7c8bf5ed5c8cf79de8c9bd6ef00d15c0b75d700dc5659de878b694
|
3 |
size 88042
|
ppo-LunarLander-v2/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 43634
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a7a3fb9b4c794e5e19da1a04e2717388ae08f1aacd5e2ead2a353cbe0d92315a
|
3 |
size 43634
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 243.3706643, "std_reward": 83.63753790852923, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-10-19T20:12:37.571446"}
|