Initial commit
Browse files- README.md +1 -1
- args.yml +9 -9
- ppo-seals-HalfCheetah-v0.zip +2 -2
- ppo-seals-HalfCheetah-v0/data +19 -19
- ppo-seals-HalfCheetah-v0/policy.optimizer.pth +2 -2
- ppo-seals-HalfCheetah-v0/policy.pth +1 -1
- replay.mp4 +2 -2
- results.json +1 -1
- train_eval_metrics.zip +2 -2
- vec_normalize.pkl +1 -1
README.md
CHANGED
|
@@ -10,7 +10,7 @@ model-index:
|
|
| 10 |
results:
|
| 11 |
- metrics:
|
| 12 |
- type: mean_reward
|
| 13 |
-
value:
|
| 14 |
name: mean_reward
|
| 15 |
task:
|
| 16 |
type: reinforcement-learning
|
|
|
|
| 10 |
results:
|
| 11 |
- metrics:
|
| 12 |
- type: mean_reward
|
| 13 |
+
value: 2682.42 +/- 265.45
|
| 14 |
name: mean_reward
|
| 15 |
task:
|
| 16 |
type: reinforcement-learning
|
args.yml
CHANGED
|
@@ -12,13 +12,15 @@
|
|
| 12 |
- - eval_freq
|
| 13 |
- 25000
|
| 14 |
- - gym_packages
|
| 15 |
-
-
|
| 16 |
- - hyperparams
|
| 17 |
- null
|
| 18 |
- - log_folder
|
| 19 |
-
-
|
| 20 |
- - log_interval
|
| 21 |
- -1
|
|
|
|
|
|
|
| 22 |
- - n_eval_envs
|
| 23 |
- 1
|
| 24 |
- - n_evaluations
|
|
@@ -34,7 +36,7 @@
|
|
| 34 |
- - no_optim_plots
|
| 35 |
- false
|
| 36 |
- - num_threads
|
| 37 |
-
-
|
| 38 |
- - optimization_log_path
|
| 39 |
- null
|
| 40 |
- - optimize_hyperparameters
|
|
@@ -48,17 +50,15 @@
|
|
| 48 |
- - save_replay_buffer
|
| 49 |
- false
|
| 50 |
- - seed
|
| 51 |
-
-
|
| 52 |
- - storage
|
| 53 |
- null
|
| 54 |
- - study_name
|
| 55 |
- null
|
| 56 |
- - tensorboard_log
|
| 57 |
-
-
|
| 58 |
-
- - total_n_trials
|
| 59 |
-
- null
|
| 60 |
- - track
|
| 61 |
-
-
|
| 62 |
- - trained_agent
|
| 63 |
- ''
|
| 64 |
- - truncate_last_trajectory
|
|
@@ -72,4 +72,4 @@
|
|
| 72 |
- - wandb_entity
|
| 73 |
- null
|
| 74 |
- - wandb_project_name
|
| 75 |
-
-
|
|
|
|
| 12 |
- - eval_freq
|
| 13 |
- 25000
|
| 14 |
- - gym_packages
|
| 15 |
+
- - seals
|
| 16 |
- - hyperparams
|
| 17 |
- null
|
| 18 |
- - log_folder
|
| 19 |
+
- seals_experts_wandb_oldpickle/seed_3/
|
| 20 |
- - log_interval
|
| 21 |
- -1
|
| 22 |
+
- - max_total_trials
|
| 23 |
+
- null
|
| 24 |
- - n_eval_envs
|
| 25 |
- 1
|
| 26 |
- - n_evaluations
|
|
|
|
| 36 |
- - no_optim_plots
|
| 37 |
- false
|
| 38 |
- - num_threads
|
| 39 |
+
- 1
|
| 40 |
- - optimization_log_path
|
| 41 |
- null
|
| 42 |
- - optimize_hyperparameters
|
|
|
|
| 50 |
- - save_replay_buffer
|
| 51 |
- false
|
| 52 |
- - seed
|
| 53 |
+
- 3
|
| 54 |
- - storage
|
| 55 |
- null
|
| 56 |
- - study_name
|
| 57 |
- null
|
| 58 |
- - tensorboard_log
|
| 59 |
+
- runs/seals/HalfCheetah-v0__ppo__3__1658844020
|
|
|
|
|
|
|
| 60 |
- - track
|
| 61 |
+
- true
|
| 62 |
- - trained_agent
|
| 63 |
- ''
|
| 64 |
- - truncate_last_trajectory
|
|
|
|
| 72 |
- - wandb_entity
|
| 73 |
- null
|
| 74 |
- - wandb_project_name
|
| 75 |
+
- seals-experts-oldpickle
|
ppo-seals-HalfCheetah-v0.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 sha256:0d84b4f1d99e0ddcfe9a04712e134aa6d30ea3a8474f349334fce36f326f6342
|
| 3 |
+
size 170249
|
ppo-seals-HalfCheetah-v0/data
CHANGED
|
@@ -4,19 +4,19 @@
|
|
| 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 sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\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 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 |
-
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at
|
| 14 |
-
"_predict": "<function ActorCriticPolicy._predict at
|
| 15 |
-
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at
|
| 16 |
-
"get_distribution": "<function ActorCriticPolicy.get_distribution at
|
| 17 |
-
"predict_values": "<function ActorCriticPolicy.predict_values at
|
| 18 |
"__abstractmethods__": "frozenset()",
|
| 19 |
-
"_abc_impl": "<_abc_data object at
|
| 20 |
},
|
| 21 |
"verbose": 1,
|
| 22 |
"policy_kwargs": {
|
|
@@ -68,15 +68,15 @@
|
|
| 68 |
"_num_timesteps_at_start": 0,
|
| 69 |
"seed": 0,
|
| 70 |
"action_noise": null,
|
| 71 |
-
"start_time":
|
| 72 |
"learning_rate": {
|
| 73 |
":type:": "<class 'function'>",
|
| 74 |
-
":serialized:": "
|
| 75 |
},
|
| 76 |
-
"tensorboard_log":
|
| 77 |
"lr_schedule": {
|
| 78 |
":type:": "<class 'function'>",
|
| 79 |
-
":serialized:": "
|
| 80 |
},
|
| 81 |
"_last_obs": null,
|
| 82 |
"_last_episode_starts": {
|
|
@@ -85,7 +85,7 @@
|
|
| 85 |
},
|
| 86 |
"_last_original_obs": {
|
| 87 |
":type:": "<class 'numpy.ndarray'>",
|
| 88 |
-
":serialized:": "
|
| 89 |
},
|
| 90 |
"_episode_num": 0,
|
| 91 |
"use_sde": false,
|
|
@@ -93,7 +93,7 @@
|
|
| 93 |
"_current_progress_remaining": -0.00044800000000000395,
|
| 94 |
"ep_info_buffer": {
|
| 95 |
":type:": "<class 'collections.deque'>",
|
| 96 |
-
":serialized:": "gAWVgRAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////
|
| 97 |
},
|
| 98 |
"ep_success_buffer": {
|
| 99 |
":type:": "<class 'collections.deque'>",
|
|
@@ -110,7 +110,7 @@
|
|
| 110 |
"n_epochs": 5,
|
| 111 |
"clip_range": {
|
| 112 |
":type:": "<class 'function'>",
|
| 113 |
-
":serialized:": "
|
| 114 |
},
|
| 115 |
"clip_range_vf": null,
|
| 116 |
"normalize_advantage": true,
|
|
|
|
| 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 sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\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 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 0x7f3998e418b0>",
|
| 8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f3998e41940>",
|
| 9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f3998e419d0>",
|
| 10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f3998e41a60>",
|
| 11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f3998e41af0>",
|
| 12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f3998e41b80>",
|
| 13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f3998e41c10>",
|
| 14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f3998e41ca0>",
|
| 15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f3998e41d30>",
|
| 16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f3998e41dc0>",
|
| 17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f3998e41e50>",
|
| 18 |
"__abstractmethods__": "frozenset()",
|
| 19 |
+
"_abc_impl": "<_abc_data object at 0x7f3998e36e70>"
|
| 20 |
},
|
| 21 |
"verbose": 1,
|
| 22 |
"policy_kwargs": {
|
|
|
|
| 68 |
"_num_timesteps_at_start": 0,
|
| 69 |
"seed": 0,
|
| 70 |
"action_noise": null,
|
| 71 |
+
"start_time": 1658844023.7846022,
|
| 72 |
"learning_rate": {
|
| 73 |
":type:": "<class 'function'>",
|
| 74 |
+
":serialized:": "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"
|
| 75 |
},
|
| 76 |
+
"tensorboard_log": "runs/seals/HalfCheetah-v0__ppo__3__1658844020/seals-HalfCheetah-v0",
|
| 77 |
"lr_schedule": {
|
| 78 |
":type:": "<class 'function'>",
|
| 79 |
+
":serialized:": "gAWVhQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAEsBSwFLE0MEiABTAJROhZQpjAFflIWUjFUvaG9tZS9tYXhpbWlsaWFuLy5sb2NhbC9saWIvcHl0aG9uMy44L3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flGgNdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpSMHGNsb3VkcGlja2xlLmNsb3VkcGlja2xlX2Zhc3SUjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoH32UfZQoaBdoDowMX19xdWFsbmFtZV9flIwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5SMD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBiMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHPzWKdLD3DSmFlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="
|
| 80 |
},
|
| 81 |
"_last_obs": null,
|
| 82 |
"_last_episode_starts": {
|
|
|
|
| 85 |
},
|
| 86 |
"_last_original_obs": {
|
| 87 |
":type:": "<class 'numpy.ndarray'>",
|
| 88 |
+
":serialized:": "gAWVBQEAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaQAAAAAAAAAAB2Z+QbXKc/jT0mHE5Zqb9Abkxvd52nP0C+REr2N6U/+AwnlwECmj8wrkHHAsuHv800Ivm4Cqu/faYiehydr7/8cdbMid6pP3OQP3pTJLg/MDfEPKJsqb9GwgK9gd/BP+3nrSt0TJu/HJISpgOCpT/bkVyWARSAP2io0OUiero/t1M3Irhkwr8E2UhsW1Zzv5SMBW51bXB5lIwFZHR5cGWUk5SMAmY4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsShpSMAUOUdJRSlC4="
|
| 89 |
},
|
| 90 |
"_episode_num": 0,
|
| 91 |
"use_sde": false,
|
|
|
|
| 93 |
"_current_progress_remaining": -0.00044800000000000395,
|
| 94 |
"ep_info_buffer": {
|
| 95 |
":type:": "<class 'collections.deque'>",
|
| 96 |
+
":serialized:": "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"
|
| 97 |
},
|
| 98 |
"ep_success_buffer": {
|
| 99 |
":type:": "<class 'collections.deque'>",
|
|
|
|
| 110 |
"n_epochs": 5,
|
| 111 |
"clip_range": {
|
| 112 |
":type:": "<class 'function'>",
|
| 113 |
+
":serialized:": "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"
|
| 114 |
},
|
| 115 |
"clip_range_vf": null,
|
| 116 |
"normalize_advantage": true,
|
ppo-seals-HalfCheetah-v0/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 sha256:716ea6ef6d3a6a4bc583acddc47dbaf2b7ee84db7a5fe820f256b6b59d512470
|
| 3 |
+
size 99504
|
ppo-seals-HalfCheetah-v0/policy.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 49022
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b085ce0b30d383a5848af9a358b75af0fcca4eb4021dc56e0bf41d079a9705c5
|
| 3 |
size 49022
|
replay.mp4
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 sha256:85a21f865d7c967f4b4090d9337185274836b3a39d4544c44d9826e41960172a
|
| 3 |
+
size 1500915
|
results.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"mean_reward":
|
|
|
|
| 1 |
+
{"mean_reward": 2682.4200444, "std_reward": 265.44861435886105, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-07-27T17:00:53.794476"}
|
train_eval_metrics.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 sha256:25ce896f744515caf0d8ffb207366f55696b391692d3ba18ef49a521493c20c9
|
| 3 |
+
size 33532
|
vec_normalize.pkl
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4770
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fdf67571a10030cda928a9a07bd7350a9583355800817c61f0b1e84071a535a5
|
| 3 |
size 4770
|