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 +30 -30
- 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: 232.06 +/- 50.03
|
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 0x7f362cd62440>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f362cd624d0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f362cd62560>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f362cd625f0>", "_build": "<function ActorCriticPolicy._build at 0x7f362cd62680>", "forward": "<function ActorCriticPolicy.forward at 0x7f362cd62710>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f362cd627a0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f362cd62830>", "_predict": "<function ActorCriticPolicy._predict at 0x7f362cd628c0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f362cd62950>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f362cd629e0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f362cd62a70>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f362cd65240>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 2016000, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1692562220624020076, "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:": "gAWVswAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiS0CFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.008000000000000007, "_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": 450, "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": 64, "n_steps": 700, "gamma": 0.99, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 32, "n_epochs": 10, "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:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "system_info": {"OS": "Linux-5.15.109+-x86_64-with-glibc2.35 # 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": "1.23.5", "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 0x7cc39ac5d870>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7cc39ac5d900>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7cc39ac5d990>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7cc39ac5da20>", "_build": "<function ActorCriticPolicy._build at 0x7cc39ac5dab0>", "forward": "<function ActorCriticPolicy.forward at 0x7cc39ac5db40>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7cc39ac5dbd0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7cc39ac5dc60>", "_predict": "<function ActorCriticPolicy._predict at 0x7cc39ac5dcf0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7cc39ac5dd80>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7cc39ac5de10>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7cc39ac5dea0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7cc3a3df0840>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 5001304, "_total_timesteps": 5000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1692629405413708352, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAM1ut7yD4Bk/ql5HvVrAH79HBZi90J2VvQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -0.00026079999999994996, "_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": 9884, "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": "Generator(PCG64)"}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "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", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": "Generator(PCG64)"}, "n_envs": 1, "n_steps": 2024, "gamma": 0.98, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 128, "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:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "system_info": {"OS": "Linux-5.15.109+-x86_64-with-glibc2.35 # 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": "1.23.5", "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 sha256:60d1187321f5fa4e1b898b54922ec8591499aecfc847dc38c39d68728d0dd857
|
3 |
+
size 146476
|
ppo-LunarLander-v2/data
CHANGED
@@ -4,57 +4,57 @@
|
|
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'>",
|
38 |
-
":serialized:": "
|
39 |
},
|
40 |
"_last_original_obs": null,
|
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:": "
|
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]",
|
@@ -65,26 +65,26 @@
|
|
65 |
"high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]",
|
66 |
"low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]",
|
67 |
"high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]",
|
68 |
-
"_np_random":
|
69 |
},
|
70 |
"action_space": {
|
71 |
":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
|
72 |
-
":serialized:": "
|
73 |
"n": "4",
|
74 |
"start": "0",
|
75 |
"_shape": [],
|
76 |
"dtype": "int64",
|
77 |
-
"_np_random":
|
78 |
},
|
79 |
-
"n_envs":
|
80 |
-
"n_steps":
|
81 |
-
"gamma": 0.
|
82 |
"gae_lambda": 0.98,
|
83 |
"ent_coef": 0.01,
|
84 |
"vf_coef": 0.5,
|
85 |
"max_grad_norm": 0.5,
|
86 |
-
"batch_size":
|
87 |
-
"n_epochs":
|
88 |
"clip_range": {
|
89 |
":type:": "<class 'function'>",
|
90 |
":serialized:": "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"
|
|
|
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 0x7cc39ac5d870>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7cc39ac5d900>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7cc39ac5d990>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7cc39ac5da20>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7cc39ac5dab0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7cc39ac5db40>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7cc39ac5dbd0>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7cc39ac5dc60>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7cc39ac5dcf0>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7cc39ac5dd80>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7cc39ac5de10>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7cc39ac5dea0>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7cc3a3df0840>"
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
24 |
+
"num_timesteps": 5001304,
|
25 |
+
"_total_timesteps": 5000000,
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
+
"start_time": 1692629405413708352,
|
30 |
"learning_rate": 0.0003,
|
31 |
"tensorboard_log": null,
|
32 |
"_last_obs": {
|
33 |
":type:": "<class 'numpy.ndarray'>",
|
34 |
+
":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAM1ut7yD4Bk/ql5HvVrAH79HBZi90J2VvQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
|
35 |
},
|
36 |
"_last_episode_starts": {
|
37 |
":type:": "<class 'numpy.ndarray'>",
|
38 |
+
":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
|
39 |
},
|
40 |
"_last_original_obs": null,
|
41 |
"_episode_num": 0,
|
42 |
"use_sde": false,
|
43 |
"sde_sample_freq": -1,
|
44 |
+
"_current_progress_remaining": -0.00026079999999994996,
|
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": 9884,
|
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]",
|
|
|
65 |
"high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]",
|
66 |
"low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]",
|
67 |
"high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]",
|
68 |
+
"_np_random": "Generator(PCG64)"
|
69 |
},
|
70 |
"action_space": {
|
71 |
":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
|
72 |
+
":serialized:": "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",
|
73 |
"n": "4",
|
74 |
"start": "0",
|
75 |
"_shape": [],
|
76 |
"dtype": "int64",
|
77 |
+
"_np_random": "Generator(PCG64)"
|
78 |
},
|
79 |
+
"n_envs": 1,
|
80 |
+
"n_steps": 2024,
|
81 |
+
"gamma": 0.98,
|
82 |
"gae_lambda": 0.98,
|
83 |
"ent_coef": 0.01,
|
84 |
"vf_coef": 0.5,
|
85 |
"max_grad_norm": 0.5,
|
86 |
+
"batch_size": 128,
|
87 |
+
"n_epochs": 4,
|
88 |
"clip_range": {
|
89 |
":type:": "<class 'function'>",
|
90 |
":serialized:": "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"
|
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 sha256:5889634514e628c399be1e8f2bf3b52ce6e31f8ef225ff6f42fe4ddeb4d88588
|
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 sha256:608917a1a2a9ba3a7ca70c406090ffd8ee6068738393fda7606847d9fd8ff57e
|
3 |
size 43329
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 232.05633497628278, "std_reward": 50.02507526649312, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-08-21T17:46:22.488627"}
|