Commit
•
ed09719
1
Parent(s):
d0d7c97
Upload PPO LunarLander-v2 trained agent
Browse files- README.md +1 -1
- config.json +1 -1
- ppo-LunarLander-v2-2.zip +1 -1
- ppo-LunarLander-v2-2/data +2 -2
- ppo-LunarLander-v2-2/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: -92.97 +/- 43.74
|
| 20 |
name: mean_reward
|
| 21 |
verified: false
|
| 22 |
---
|
config.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ", "__init__": "<function ActorCriticPolicy.__init__ at 0x7f228fb2fe20>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f228fb2feb0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f228fb2ff40>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f228fb48040>", "_build": "<function ActorCriticPolicy._build at 0x7f228fb480d0>", "forward": "<function ActorCriticPolicy.forward at 0x7f228fb48160>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f228fb481f0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f228fb48280>", "_predict": "<function ActorCriticPolicy._predict at 0x7f228fb48310>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f228fb483a0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f228fb48430>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f228fb484c0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f228fb443c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 0, "_total_timesteps": 10000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time":
|
|
|
|
| 1 |
+
{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ", "__init__": "<function ActorCriticPolicy.__init__ at 0x7f228fb2fe20>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f228fb2feb0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f228fb2ff40>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f228fb48040>", "_build": "<function ActorCriticPolicy._build at 0x7f228fb480d0>", "forward": "<function ActorCriticPolicy.forward at 0x7f228fb48160>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f228fb481f0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f228fb48280>", "_predict": "<function ActorCriticPolicy._predict at 0x7f228fb48310>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f228fb483a0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f228fb48430>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f228fb484c0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f228fb443c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 0, "_total_timesteps": 10000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1698207138287156101, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAEBAQEBAQEBAQEBAQEBAQGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 1.0, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 0, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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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": 2048, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 10240, "n_epochs": 5, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.5.6-76060506-generic-x86_64-with-glibc2.35 # 202310061235~1697396945~22.04~9283e32 SMP PREEMPT_DYNAMIC Sun O", "Python": "3.10.12", "Stable-Baselines3": "2.1.0", "PyTorch": "2.1.0", "GPU Enabled": "True", "Numpy": "1.22.4", "Cloudpickle": "3.0.0", "Gymnasium": "0.28.1"}}
|
ppo-LunarLander-v2-2.zip
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 56717
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf24a4b0432430bc22a24ffadcd93ccfc2420c5fb7b72b87f55e23aac51983f1
|
| 3 |
size 56717
|
ppo-LunarLander-v2-2/data
CHANGED
|
@@ -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'>",
|
|
|
|
| 26 |
"_num_timesteps_at_start": 0,
|
| 27 |
"seed": null,
|
| 28 |
"action_noise": null,
|
| 29 |
+
"start_time": 1698207138287156101,
|
| 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'>",
|
ppo-LunarLander-v2-2/policy.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 43762
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eb141585f919e5264fb79a8034c5d8de2a548c49e09457ed7418cf94bc7e6705
|
| 3 |
size 43762
|
results.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"mean_reward": -
|
|
|
|
| 1 |
+
{"mean_reward": -92.9704844, "std_reward": 43.7440458674056, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-10-25T14:12:20.139122"}
|