Commit
•
2814623
1
Parent(s):
4abebfe
Unit1 - LunarLander-v2 - PPO - 1M steps
Browse files- README.md +1 -1
- config.json +1 -1
- ppo-LunarLander-v2-optimized.zip +2 -2
- ppo-LunarLander-v2-optimized/data +25 -25
- ppo-LunarLander-v2-optimized/policy.optimizer.pth +2 -2
- ppo-LunarLander-v2-optimized/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: 269.15 +/- 17.65
|
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 0x7f27edcd3490>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f27edcd3520>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f27edcd35b0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f27edcd3640>", "_build": "<function ActorCriticPolicy._build at 0x7f27edcd36d0>", "forward": "<function ActorCriticPolicy.forward at 0x7f27edcd3760>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f27edcd37f0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f27edcd3880>", "_predict": "<function ActorCriticPolicy._predict at 0x7f27edcd3910>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f27edcd39a0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f27edcd3a30>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f27edcd3ac0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f27efd57680>"}, "verbose": 0, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gAWVdAAAAAAAAAB9lCiMCG5ldF9hcmNolH2UKIwCcGmUXZQoSyBLIGWMAnZmlF2UKEsgSyBldYwNYWN0aXZhdGlvbl9mbpSMG3RvcmNoLm5uLm1vZHVsZXMuYWN0aXZhdGlvbpSMBVJlTFU2lJOUjApvcnRob19pbml0lIl1Lg==", "net_arch": {"pi": [32, 32], "vf": [32, 32]}, "activation_fn": "<class 'torch.nn.modules.activation.ReLU6'>", "ortho_init": false}, "num_timesteps": 106496, "_total_timesteps": 100000.0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1704355086503668162, "learning_rate": 0.004713681965880727, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVkwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksghZSMAUOUdJRSlC4="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.0649599999999999, "_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": 130, "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": 32, "n_steps": 256, "gamma": 0.9990589806615283, "gae_lambda": 0.8969327195179122, "ent_coef": 1.213373552278969e-05, "vf_coef": 0.6187611603371788, "max_grad_norm": 2.7230307780661405, "rollout_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVNgAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwNUm9sbG91dEJ1ZmZlcpSTlC4=", "__module__": "stable_baselines3.common.buffers", "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'advantages': <class 'numpy.ndarray'>, 'returns': <class 'numpy.ndarray'>, 'episode_starts': <class 'numpy.ndarray'>, 'log_probs': <class 'numpy.ndarray'>, 'values': <class 'numpy.ndarray'>}", "__doc__": "\n Rollout buffer used in on-policy algorithms like A2C/PPO.\n It corresponds to ``buffer_size`` transitions collected\n using the current policy.\n This experience will be discarded after the policy update.\n In order to use PPO objective, we also store the current value of each state\n and the log probability of each taken action.\n\n The term rollout here refers to the model-free notion and should not\n be used with the concept of rollout used in model-based RL or planning.\n Hence, it is only involved in policy and value function training but not action selection.\n\n :param buffer_size: Max number of element in the buffer\n :param observation_space: Observation space\n :param action_space: Action space\n :param device: PyTorch device\n :param gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n Equivalent to classic advantage when set to 1.\n :param gamma: Discount factor\n :param n_envs: Number of parallel environments\n ", "__init__": "<function RolloutBuffer.__init__ at 0x7f27ee003250>", "reset": "<function RolloutBuffer.reset at 0x7f27ee0032e0>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7f27ee003370>", "add": "<function RolloutBuffer.add at 0x7f27ee003400>", "get": "<function RolloutBuffer.get at 0x7f27ee003490>", "_get_samples": "<function RolloutBuffer._get_samples at 0x7f27ee003520>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f27ee007f40>"}, "rollout_buffer_kwargs": {}, "batch_size": 64, "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:": "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"}, "system_info": {"OS": "Linux-5.15.133.1-microsoft-standard-WSL2-x86_64-with-glibc2.31 # 1 SMP Thu Oct 5 21:02:42 UTC 2023", "Python": "3.10.13", "Stable-Baselines3": "2.2.1", "PyTorch": "2.1.0.post301", "GPU Enabled": "True", "Numpy": "1.26.2", "Cloudpickle": "3.0.0", "Gymnasium": "0.28.1", "OpenAI Gym": "0.26.2"}}
|
|
|
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 0x7f57436a3490>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f57436a3520>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f57436a35b0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f57436a3640>", "_build": "<function ActorCriticPolicy._build at 0x7f57436a36d0>", "forward": "<function ActorCriticPolicy.forward at 0x7f57436a3760>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f57436a37f0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f57436a3880>", "_predict": "<function ActorCriticPolicy._predict at 0x7f57436a3910>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f57436a39a0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f57436a3a30>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f57436a3ac0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f574369aa40>"}, "verbose": 0, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gAWVdAAAAAAAAAB9lCiMCG5ldF9hcmNolH2UKIwCcGmUXZQoSyBLIGWMAnZmlF2UKEsgSyBldYwNYWN0aXZhdGlvbl9mbpSMG3RvcmNoLm5uLm1vZHVsZXMuYWN0aXZhdGlvbpSMBVJlTFU2lJOUjApvcnRob19pbml0lIl1Lg==", "net_arch": {"pi": [32, 32], "vf": [32, 32]}, "activation_fn": "<class 'torch.nn.modules.activation.ReLU6'>", "ortho_init": false}, "num_timesteps": 106496, "_total_timesteps": 100000.0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1704382920548522430, "learning_rate": 0.004713681965880727, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVkwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksghZSMAUOUdJRSlC4="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.0649599999999999, "_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": 390, "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:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 32, "n_steps": 256, "gamma": 0.9990589806615283, "gae_lambda": 0.8969327195179122, "ent_coef": 1.213373552278969e-05, "vf_coef": 0.6187611603371788, "max_grad_norm": 2.7230307780661405, "rollout_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVNgAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwNUm9sbG91dEJ1ZmZlcpSTlC4=", "__module__": "stable_baselines3.common.buffers", "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'advantages': <class 'numpy.ndarray'>, 'returns': <class 'numpy.ndarray'>, 'episode_starts': <class 'numpy.ndarray'>, 'log_probs': <class 'numpy.ndarray'>, 'values': <class 'numpy.ndarray'>}", "__doc__": "\n Rollout buffer used in on-policy algorithms like A2C/PPO.\n It corresponds to ``buffer_size`` transitions collected\n using the current policy.\n This experience will be discarded after the policy update.\n In order to use PPO objective, we also store the current value of each state\n and the log probability of each taken action.\n\n The term rollout here refers to the model-free notion and should not\n be used with the concept of rollout used in model-based RL or planning.\n Hence, it is only involved in policy and value function training but not action selection.\n\n :param buffer_size: Max number of element in the buffer\n :param observation_space: Observation space\n :param action_space: Action space\n :param device: PyTorch device\n :param gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n Equivalent to classic advantage when set to 1.\n :param gamma: Discount factor\n :param n_envs: Number of parallel environments\n ", "__init__": "<function RolloutBuffer.__init__ at 0x7f57439cf250>", "reset": "<function RolloutBuffer.reset at 0x7f57439cf2e0>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7f57439cf370>", "add": "<function RolloutBuffer.add at 0x7f57439cf400>", "get": "<function RolloutBuffer.get at 0x7f57439cf490>", "_get_samples": "<function RolloutBuffer._get_samples at 0x7f57439cf520>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f57439d7d40>"}, "rollout_buffer_kwargs": {}, "batch_size": 64, "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:": "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"}, "system_info": {"OS": "Linux-5.15.133.1-microsoft-standard-WSL2-x86_64-with-glibc2.31 # 1 SMP Thu Oct 5 21:02:42 UTC 2023", "Python": "3.10.13", "Stable-Baselines3": "2.2.1", "PyTorch": "2.1.0.post301", "GPU Enabled": "True", "Numpy": "1.26.2", "Cloudpickle": "3.0.0", "Gymnasium": "0.28.1", "OpenAI Gym": "0.26.2"}}
|
ppo-LunarLander-v2-optimized.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 sha256:5d8b36dec883bf4d2807b29cd362109cbbadf223762fcbad11396c7b58034f4a
|
3 |
+
size 68286
|
ppo-LunarLander-v2-optimized/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": 0,
|
23 |
"policy_kwargs": {
|
@@ -41,12 +41,12 @@
|
|
41 |
"_num_timesteps_at_start": 0,
|
42 |
"seed": null,
|
43 |
"action_noise": null,
|
44 |
-
"start_time":
|
45 |
"learning_rate": 0.004713681965880727,
|
46 |
"tensorboard_log": null,
|
47 |
"_last_obs": {
|
48 |
":type:": "<class 'numpy.ndarray'>",
|
49 |
-
":serialized:": "
|
50 |
},
|
51 |
"_last_episode_starts": {
|
52 |
":type:": "<class 'numpy.ndarray'>",
|
@@ -60,13 +60,13 @@
|
|
60 |
"_stats_window_size": 100,
|
61 |
"ep_info_buffer": {
|
62 |
":type:": "<class 'collections.deque'>",
|
63 |
-
":serialized:": "
|
64 |
},
|
65 |
"ep_success_buffer": {
|
66 |
":type:": "<class 'collections.deque'>",
|
67 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
68 |
},
|
69 |
-
"_n_updates":
|
70 |
"observation_space": {
|
71 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
72 |
":serialized:": "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",
|
@@ -84,7 +84,7 @@
|
|
84 |
},
|
85 |
"action_space": {
|
86 |
":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
|
87 |
-
":serialized:": "
|
88 |
"n": "4",
|
89 |
"start": "0",
|
90 |
"_shape": [],
|
@@ -104,14 +104,14 @@
|
|
104 |
"__module__": "stable_baselines3.common.buffers",
|
105 |
"__annotations__": "{'observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'advantages': <class 'numpy.ndarray'>, 'returns': <class 'numpy.ndarray'>, 'episode_starts': <class 'numpy.ndarray'>, 'log_probs': <class 'numpy.ndarray'>, 'values': <class 'numpy.ndarray'>}",
|
106 |
"__doc__": "\n Rollout buffer used in on-policy algorithms like A2C/PPO.\n It corresponds to ``buffer_size`` transitions collected\n using the current policy.\n This experience will be discarded after the policy update.\n In order to use PPO objective, we also store the current value of each state\n and the log probability of each taken action.\n\n The term rollout here refers to the model-free notion and should not\n be used with the concept of rollout used in model-based RL or planning.\n Hence, it is only involved in policy and value function training but not action selection.\n\n :param buffer_size: Max number of element in the buffer\n :param observation_space: Observation space\n :param action_space: Action space\n :param device: PyTorch device\n :param gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n Equivalent to classic advantage when set to 1.\n :param gamma: Discount factor\n :param n_envs: Number of parallel environments\n ",
|
107 |
-
"__init__": "<function RolloutBuffer.__init__ at
|
108 |
-
"reset": "<function RolloutBuffer.reset at
|
109 |
-
"compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at
|
110 |
-
"add": "<function RolloutBuffer.add at
|
111 |
-
"get": "<function RolloutBuffer.get at
|
112 |
-
"_get_samples": "<function RolloutBuffer._get_samples at
|
113 |
"__abstractmethods__": "frozenset()",
|
114 |
-
"_abc_impl": "<_abc._abc_data object at
|
115 |
},
|
116 |
"rollout_buffer_kwargs": {},
|
117 |
"batch_size": 64,
|
|
|
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 0x7f57436a3490>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f57436a3520>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f57436a35b0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f57436a3640>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f57436a36d0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f57436a3760>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f57436a37f0>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f57436a3880>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f57436a3910>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f57436a39a0>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f57436a3a30>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f57436a3ac0>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7f574369aa40>"
|
21 |
},
|
22 |
"verbose": 0,
|
23 |
"policy_kwargs": {
|
|
|
41 |
"_num_timesteps_at_start": 0,
|
42 |
"seed": null,
|
43 |
"action_noise": null,
|
44 |
+
"start_time": 1704382920548522430,
|
45 |
"learning_rate": 0.004713681965880727,
|
46 |
"tensorboard_log": null,
|
47 |
"_last_obs": {
|
48 |
":type:": "<class 'numpy.ndarray'>",
|
49 |
+
":serialized:": "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"
|
50 |
},
|
51 |
"_last_episode_starts": {
|
52 |
":type:": "<class 'numpy.ndarray'>",
|
|
|
60 |
"_stats_window_size": 100,
|
61 |
"ep_info_buffer": {
|
62 |
":type:": "<class 'collections.deque'>",
|
63 |
+
":serialized:": "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"
|
64 |
},
|
65 |
"ep_success_buffer": {
|
66 |
":type:": "<class 'collections.deque'>",
|
67 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
68 |
},
|
69 |
+
"_n_updates": 390,
|
70 |
"observation_space": {
|
71 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
72 |
":serialized:": "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",
|
|
|
84 |
},
|
85 |
"action_space": {
|
86 |
":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
|
87 |
+
":serialized:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
|
88 |
"n": "4",
|
89 |
"start": "0",
|
90 |
"_shape": [],
|
|
|
104 |
"__module__": "stable_baselines3.common.buffers",
|
105 |
"__annotations__": "{'observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'advantages': <class 'numpy.ndarray'>, 'returns': <class 'numpy.ndarray'>, 'episode_starts': <class 'numpy.ndarray'>, 'log_probs': <class 'numpy.ndarray'>, 'values': <class 'numpy.ndarray'>}",
|
106 |
"__doc__": "\n Rollout buffer used in on-policy algorithms like A2C/PPO.\n It corresponds to ``buffer_size`` transitions collected\n using the current policy.\n This experience will be discarded after the policy update.\n In order to use PPO objective, we also store the current value of each state\n and the log probability of each taken action.\n\n The term rollout here refers to the model-free notion and should not\n be used with the concept of rollout used in model-based RL or planning.\n Hence, it is only involved in policy and value function training but not action selection.\n\n :param buffer_size: Max number of element in the buffer\n :param observation_space: Observation space\n :param action_space: Action space\n :param device: PyTorch device\n :param gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n Equivalent to classic advantage when set to 1.\n :param gamma: Discount factor\n :param n_envs: Number of parallel environments\n ",
|
107 |
+
"__init__": "<function RolloutBuffer.__init__ at 0x7f57439cf250>",
|
108 |
+
"reset": "<function RolloutBuffer.reset at 0x7f57439cf2e0>",
|
109 |
+
"compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7f57439cf370>",
|
110 |
+
"add": "<function RolloutBuffer.add at 0x7f57439cf400>",
|
111 |
+
"get": "<function RolloutBuffer.get at 0x7f57439cf490>",
|
112 |
+
"_get_samples": "<function RolloutBuffer._get_samples at 0x7f57439cf520>",
|
113 |
"__abstractmethods__": "frozenset()",
|
114 |
+
"_abc_impl": "<_abc._abc_data object at 0x7f57439d7d40>"
|
115 |
},
|
116 |
"rollout_buffer_kwargs": {},
|
117 |
"batch_size": 64,
|
ppo-LunarLander-v2-optimized/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 sha256:693ceb8398fad07fd85c57cf80596bb6d1f529ada91c2f0d31d8550d530bb1d3
|
3 |
+
size 32938
|
ppo-LunarLander-v2-optimized/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15986
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c2f12a860c1e6dff04c87e03ce88976fc642be66d0d4b9e366d8b5d74fbb6ac
|
3 |
size 15986
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 269.1469207, "std_reward": 17.646590179186077, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-01-04T16:54:57.070612"}
|