initial commit
Browse files- README.md +4 -4
- config.json +1 -1
- ppo-LunarLander-v2.zip +2 -2
- ppo-LunarLander-v2/data +19 -19
- ppo-LunarLander-v2/policy.optimizer.pth +2 -2
- ppo-LunarLander-v2/policy.pth +2 -2
- ppo-LunarLander-v2/pytorch_variables.pth +2 -2
- ppo-LunarLander-v2/system_info.txt +3 -3
- replay.mp4 +0 -0
- results.json +1 -1
README.md
CHANGED
@@ -6,7 +6,7 @@ tags:
|
|
6 |
- reinforcement-learning
|
7 |
- stable-baselines3
|
8 |
model-index:
|
9 |
-
- name:
|
10 |
results:
|
11 |
- task:
|
12 |
type: reinforcement-learning
|
@@ -16,13 +16,13 @@ model-index:
|
|
16 |
type: LunarLander-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
-
value:
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
23 |
|
24 |
-
# **
|
25 |
-
This is a trained model of a **
|
26 |
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
27 |
|
28 |
## Usage (with Stable-baselines3)
|
|
|
6 |
- reinforcement-learning
|
7 |
- stable-baselines3
|
8 |
model-index:
|
9 |
+
- name: ppo
|
10 |
results:
|
11 |
- task:
|
12 |
type: reinforcement-learning
|
|
|
16 |
type: LunarLander-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
+
value: 257.21 +/- 20.40
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
23 |
|
24 |
+
# **ppo** Agent playing **LunarLander-v2**
|
25 |
+
This is a trained model of a **ppo** agent playing **LunarLander-v2**
|
26 |
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
27 |
|
28 |
## Usage (with Stable-baselines3)
|
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 0x7e6e7e272170>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7e6e7e272200>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7e6e7e272290>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7e6e7e272320>", "_build": "<function ActorCriticPolicy._build at 0x7e6e7e2723b0>", "forward": "<function ActorCriticPolicy.forward at 0x7e6e7e272440>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7e6e7e2724d0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7e6e7e272560>", "_predict": "<function ActorCriticPolicy._predict at 0x7e6e7e2725f0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7e6e7e272680>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7e6e7e272710>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7e6e7e2727a0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7e6e7e26de80>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1689446014086779231, "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:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.109+-x86_64-with-glibc2.31 # 1 SMP Fri Jun 9 10:57:30 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 0x7f01289e0790>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f01289e0820>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f01289e08b0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f01289e0940>", "_build": "<function ActorCriticPolicy._build at 0x7f01289e09d0>", "forward": "<function ActorCriticPolicy.forward at 0x7f01289e0a60>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f01289e0af0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f01289e0b80>", "_predict": "<function ActorCriticPolicy._predict at 0x7f01289e0c10>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f01289e0ca0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f01289e0d30>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f01289e0dc0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f01289e80c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1717908002460356240, "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": 252, "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-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sun Apr 28 14:29:16 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.3.0+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:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f364ad48970a24477734fbabc0536529e00fd54738b27390d687a7c732ba381
|
3 |
+
size 148084
|
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'>",
|
@@ -45,16 +45,16 @@
|
|
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:": "
|
58 |
"dtype": "float32",
|
59 |
"bounded_below": "[ True True True True True True True True]",
|
60 |
"bounded_above": "[ True True True True True True True True]",
|
@@ -69,7 +69,7 @@
|
|
69 |
},
|
70 |
"action_space": {
|
71 |
":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
|
72 |
-
":serialized:": "
|
73 |
"n": "4",
|
74 |
"start": "0",
|
75 |
"_shape": [],
|
|
|
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 0x7f01289e0790>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f01289e0820>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f01289e08b0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f01289e0940>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f01289e09d0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f01289e0a60>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f01289e0af0>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f01289e0b80>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f01289e0c10>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f01289e0ca0>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f01289e0d30>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f01289e0dc0>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7f01289e80c0>"
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
|
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
+
"start_time": 1717908002460356240,
|
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'>",
|
52 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
53 |
},
|
54 |
+
"_n_updates": 252,
|
55 |
"observation_space": {
|
56 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
57 |
+
":serialized:": "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",
|
58 |
"dtype": "float32",
|
59 |
"bounded_below": "[ True True True True True True True True]",
|
60 |
"bounded_above": "[ True True True True True True True True]",
|
|
|
69 |
},
|
70 |
"action_space": {
|
71 |
":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
|
72 |
+
":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=",
|
73 |
"n": "4",
|
74 |
"start": "0",
|
75 |
"_shape": [],
|
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 sha256:441c06abf08e6edc40bb154d0c6059418a6c8fd22ec7e17523edde3913ee1757
|
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56903cf9f1102201559205e77238b329593ae16a8f886b1b8c0529874442efe7
|
3 |
+
size 43762
|
ppo-LunarLander-v2/pytorch_variables.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 sha256:0c35cea3b2e60fb5e7e162d3592df775cd400e575a31c72f359fb9e654ab00c5
|
3 |
+
size 864
|
ppo-LunarLander-v2/system_info.txt
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
-
- OS: Linux-
|
2 |
- Python: 3.10.12
|
3 |
- Stable-Baselines3: 2.0.0a5
|
4 |
-
- PyTorch: 2.0
|
5 |
- GPU Enabled: True
|
6 |
-
- Numpy: 1.
|
7 |
- Cloudpickle: 2.2.1
|
8 |
- Gymnasium: 0.28.1
|
9 |
- OpenAI Gym: 0.25.2
|
|
|
1 |
+
- OS: Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sun Apr 28 14:29:16 UTC 2024
|
2 |
- Python: 3.10.12
|
3 |
- Stable-Baselines3: 2.0.0a5
|
4 |
+
- PyTorch: 2.3.0+cu121
|
5 |
- GPU Enabled: True
|
6 |
+
- Numpy: 1.25.2
|
7 |
- Cloudpickle: 2.2.1
|
8 |
- Gymnasium: 0.28.1
|
9 |
- OpenAI Gym: 0.25.2
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 257.20506370000004, "std_reward": 20.3995272702413, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-06-09T05:21:37.002620"}
|