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 +7 -7
- 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: 243.71 +/- 70.12
|
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 0x7cb8599cee60>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7cb8599ceef0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7cb8599cef80>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7cb8599cf010>", "_build": "<function ActorCriticPolicy._build at 0x7cb8599cf0a0>", "forward": "<function ActorCriticPolicy.forward at 0x7cb8599cf130>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7cb8599cf1c0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7cb8599cf250>", "_predict": "<function ActorCriticPolicy._predict at 0x7cb8599cf2e0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7cb8599cf370>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7cb8599cf400>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7cb8599cf490>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7cb8677bfbc0>"}, "verbose": 0, "policy_kwargs": {}, "num_timesteps": 100352, "_total_timesteps": 100000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1711229307962232463, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAEbDPT4E2rk+mtiAPUQ75b25pxe+IGRlPQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -0.0035199999999999676, "_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": 392, "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": 1, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.2.1+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "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 0x7cb8599cee60>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7cb8599ceef0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7cb8599cef80>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7cb8599cf010>", "_build": "<function ActorCriticPolicy._build at 0x7cb8599cf0a0>", "forward": "<function ActorCriticPolicy.forward at 0x7cb8599cf130>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7cb8599cf1c0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7cb8599cf250>", "_predict": "<function ActorCriticPolicy._predict at 0x7cb8599cf2e0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7cb8599cf370>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7cb8599cf400>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7cb8599cf490>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7cb8677bfbc0>"}, "verbose": 0, "policy_kwargs": {}, "num_timesteps": 1000448, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1711232163558762229, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAEPsXr7ZN64+uj7bPafHnr4qjjm9zmkVvQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -0.00044800000000000395, "_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": 4300, "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": 1, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.2.1+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:d4870f9da22b6d8660fc953397be0b685e1ece5b6a01d81e42cc40caa5c73ec1
|
3 |
+
size 147394
|
ppo-LunarLander-v2/data
CHANGED
@@ -21,17 +21,17 @@
|
|
21 |
},
|
22 |
"verbose": 0,
|
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'>",
|
@@ -41,17 +41,17 @@
|
|
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:": "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",
|
|
|
21 |
},
|
22 |
"verbose": 0,
|
23 |
"policy_kwargs": {},
|
24 |
+
"num_timesteps": 1000448,
|
25 |
+
"_total_timesteps": 1000000,
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
+
"start_time": 1711232163558762229,
|
30 |
"learning_rate": 0.0003,
|
31 |
"tensorboard_log": null,
|
32 |
"_last_obs": {
|
33 |
":type:": "<class 'numpy.ndarray'>",
|
34 |
+
":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAEPsXr7ZN64+uj7bPafHnr4qjjm9zmkVvQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
|
35 |
},
|
36 |
"_last_episode_starts": {
|
37 |
":type:": "<class 'numpy.ndarray'>",
|
|
|
41 |
"_episode_num": 0,
|
42 |
"use_sde": false,
|
43 |
"sde_sample_freq": -1,
|
44 |
+
"_current_progress_remaining": -0.00044800000000000395,
|
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": 4300,
|
55 |
"observation_space": {
|
56 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
57 |
":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 88362
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:85261e3d4853e25bf4d3a542e99506d8a0b6ea7b64d5a79a76bb6b18419b8446
|
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 43762
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce99e4b07a532501a82ee260cfe062c189fc123ac6e6bd5c61f9cb1faa86dd9e
|
3 |
size 43762
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 243.7081048, "std_reward": 70.11875443422355, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-23T23:12:49.231236"}
|