Initial model
Browse files- README.md +1 -1
- config.json +1 -1
- ppo-LunarLander-v2.zip +1 -1
- ppo-LunarLander-v2/data +13 -13
- 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: 277.47 +/- 26.59
|
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 0x7fb609d5b400>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fb609d5b490>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fb609d5b520>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fb609d5b5b0>", "_build": "<function ActorCriticPolicy._build at 0x7fb609d5b640>", "forward": "<function ActorCriticPolicy.forward at 0x7fb609d5b6d0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fb609d5b760>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fb609d5b7f0>", "_predict": "<function ActorCriticPolicy._predict at 0x7fb609d5b880>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fb609d5b910>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fb609d5b9a0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fb609d5ba30>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fb609d56600>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWViAAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "num_timesteps": 2015232, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1677149747168572621, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": null, "_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": -0.007616000000000067, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 492, "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, "system_info": {"OS": "Linux-6.1.11-100.fc36.x86_64-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Feb 9 20:36:30 UTC 2023", "Python": "3.10.9", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu117", "GPU Enabled": "True", "Numpy": "1.24.2", "Gym": "0.21.0"}}
|
|
|
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 0x7fd93ba4f400>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fd93ba4f490>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fd93ba4f520>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fd93ba4f5b0>", "_build": "<function ActorCriticPolicy._build at 0x7fd93ba4f640>", "forward": "<function ActorCriticPolicy.forward at 0x7fd93ba4f6d0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fd93ba4f760>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fd93ba4f7f0>", "_predict": "<function ActorCriticPolicy._predict at 0x7fd93ba4f880>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fd93ba4f910>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fd93ba4f9a0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fd93ba4fa30>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fd93ba51c80>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWViAAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "num_timesteps": 2015232, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1677149747168572621, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": null, "_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": -0.007616000000000067, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 492, "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:": "gAWVjwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMXS9ob21lL2RuZXdtYW4vQUkvdmVudnMvYXRhcmkvbGliNjQvcHl0aG9uMy4xMC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4JDAgQBlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5RoDHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB59lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-6.1.11-100.fc36.x86_64-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Feb 9 20:36:30 UTC 2023", "Python": "3.10.9", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu117", "GPU Enabled": "True", "Numpy": "1.24.2", "Gym": "0.21.0"}}
|
ppo-LunarLander-v2.zip
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 146406
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e3172a8681c6f923729ddc8f4b5badce07ccfaad977a47a313afd118f9925fc
|
3 |
size 146406
|
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": {},
|
|
|
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 0x7fd93ba4f400>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fd93ba4f490>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fd93ba4f520>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fd93ba4f5b0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7fd93ba4f640>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7fd93ba4f6d0>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7fd93ba4f760>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fd93ba4f7f0>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7fd93ba4f880>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fd93ba4f910>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fd93ba4f9a0>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7fd93ba4fa30>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7fd93ba51c80>"
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 277.47112944186, "std_reward": 26.591552231896348, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-24T16:06:08.006601"}
|