Initial commit
Browse files- README.md +19 -7
- args.yml +11 -5
- config.yml +12 -2
- ppo-seals-Humanoid-v0.zip +2 -2
- ppo-seals-Humanoid-v0/_stable_baselines3_version +1 -1
- ppo-seals-Humanoid-v0/data +24 -23
- ppo-seals-Humanoid-v0/policy.optimizer.pth +2 -2
- ppo-seals-Humanoid-v0/policy.pth +2 -2
- ppo-seals-Humanoid-v0/system_info.txt +2 -2
- replay.mp4 +2 -2
- results.json +1 -1
- train_eval_metrics.zip +2 -2
- vec_normalize.pkl +2 -2
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
|
|
@@ -37,15 +37,21 @@ SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
|
|
| 37 |
|
| 38 |
```
|
| 39 |
# Download model and save it into the logs/ folder
|
| 40 |
-
python -m
|
| 41 |
python enjoy.py --algo ppo --env seals/Humanoid-v0 -f logs/
|
| 42 |
```
|
| 43 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
## Training (with the RL Zoo)
|
| 45 |
```
|
| 46 |
python train.py --algo ppo --env seals/Humanoid-v0 -f logs/
|
| 47 |
# Upload the model and generate video (when possible)
|
| 48 |
-
python -m
|
| 49 |
```
|
| 50 |
|
| 51 |
## Hyperparameters
|
|
@@ -61,11 +67,17 @@ OrderedDict([('batch_size', 256),
|
|
| 61 |
('n_epochs', 20),
|
| 62 |
('n_steps', 2048),
|
| 63 |
('n_timesteps', 10000000.0),
|
| 64 |
-
('normalize',
|
|
|
|
| 65 |
('policy', 'MlpPolicy'),
|
| 66 |
('policy_kwargs',
|
| 67 |
-
'
|
| 68 |
-
|
|
|
|
| 69 |
('vf_coef', 0.819262464558427),
|
| 70 |
-
('normalize_kwargs',
|
|
|
|
|
|
|
|
|
|
|
|
|
| 71 |
```
|
|
|
|
| 10 |
results:
|
| 11 |
- metrics:
|
| 12 |
- type: mean_reward
|
| 13 |
+
value: 2242.51 +/- 858.20
|
| 14 |
name: mean_reward
|
| 15 |
task:
|
| 16 |
type: reinforcement-learning
|
|
|
|
| 37 |
|
| 38 |
```
|
| 39 |
# Download model and save it into the logs/ folder
|
| 40 |
+
python -m rl_zoo3.load_from_hub --algo ppo --env seals/Humanoid-v0 -orga HumanCompatibleAI -f logs/
|
| 41 |
python enjoy.py --algo ppo --env seals/Humanoid-v0 -f logs/
|
| 42 |
```
|
| 43 |
|
| 44 |
+
If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
|
| 45 |
+
```
|
| 46 |
+
python -m rl_zoo3.load_from_hub --algo ppo --env seals/Humanoid-v0 -orga HumanCompatibleAI -f logs/
|
| 47 |
+
rl_zoo3 enjoy --algo ppo --env seals/Humanoid-v0 -f logs/
|
| 48 |
+
```
|
| 49 |
+
|
| 50 |
## Training (with the RL Zoo)
|
| 51 |
```
|
| 52 |
python train.py --algo ppo --env seals/Humanoid-v0 -f logs/
|
| 53 |
# Upload the model and generate video (when possible)
|
| 54 |
+
python -m rl_zoo3.push_to_hub --algo ppo --env seals/Humanoid-v0 -f logs/ -orga HumanCompatibleAI
|
| 55 |
```
|
| 56 |
|
| 57 |
## Hyperparameters
|
|
|
|
| 67 |
('n_epochs', 20),
|
| 68 |
('n_steps', 2048),
|
| 69 |
('n_timesteps', 10000000.0),
|
| 70 |
+
('normalize',
|
| 71 |
+
{'gamma': 0.999, 'norm_obs': False, 'norm_reward': True}),
|
| 72 |
('policy', 'MlpPolicy'),
|
| 73 |
('policy_kwargs',
|
| 74 |
+
{'activation_fn': <class 'torch.nn.modules.activation.ReLU'>,
|
| 75 |
+
'features_extractor_class': <class 'imitation.policies.base.NormalizeFeaturesExtractor'>,
|
| 76 |
+
'net_arch': [{'pi': [256, 256], 'vf': [256, 256]}]}),
|
| 77 |
('vf_coef', 0.819262464558427),
|
| 78 |
+
('normalize_kwargs',
|
| 79 |
+
{'norm_obs': {'gamma': 0.999,
|
| 80 |
+
'norm_obs': False,
|
| 81 |
+
'norm_reward': True},
|
| 82 |
+
'norm_reward': False})])
|
| 83 |
```
|
args.yml
CHANGED
|
@@ -1,6 +1,8 @@
|
|
| 1 |
!!python/object/apply:collections.OrderedDict
|
| 2 |
- - - algo
|
| 3 |
- ppo
|
|
|
|
|
|
|
| 4 |
- - device
|
| 5 |
- cpu
|
| 6 |
- - env
|
|
@@ -16,7 +18,7 @@
|
|
| 16 |
- - hyperparams
|
| 17 |
- null
|
| 18 |
- - log_folder
|
| 19 |
-
-
|
| 20 |
- - log_interval
|
| 21 |
- -1
|
| 22 |
- - max_total_trials
|
|
@@ -41,6 +43,8 @@
|
|
| 41 |
- null
|
| 42 |
- - optimize_hyperparameters
|
| 43 |
- false
|
|
|
|
|
|
|
| 44 |
- - pruner
|
| 45 |
- median
|
| 46 |
- - sampler
|
|
@@ -50,13 +54,13 @@
|
|
| 50 |
- - save_replay_buffer
|
| 51 |
- false
|
| 52 |
- - seed
|
| 53 |
-
-
|
| 54 |
- - storage
|
| 55 |
- null
|
| 56 |
- - study_name
|
| 57 |
- null
|
| 58 |
- - tensorboard_log
|
| 59 |
-
- runs/seals/Humanoid-
|
| 60 |
- - track
|
| 61 |
- true
|
| 62 |
- - trained_agent
|
|
@@ -70,6 +74,8 @@
|
|
| 70 |
- - verbose
|
| 71 |
- 1
|
| 72 |
- - wandb_entity
|
| 73 |
-
-
|
| 74 |
- - wandb_project_name
|
| 75 |
-
- seals-experts-
|
|
|
|
|
|
|
|
|
| 1 |
!!python/object/apply:collections.OrderedDict
|
| 2 |
- - - algo
|
| 3 |
- ppo
|
| 4 |
+
- - conf_file
|
| 5 |
+
- hyperparams/python/ppo.py
|
| 6 |
- - device
|
| 7 |
- cpu
|
| 8 |
- - env
|
|
|
|
| 18 |
- - hyperparams
|
| 19 |
- null
|
| 20 |
- - log_folder
|
| 21 |
+
- logs
|
| 22 |
- - log_interval
|
| 23 |
- -1
|
| 24 |
- - max_total_trials
|
|
|
|
| 43 |
- null
|
| 44 |
- - optimize_hyperparameters
|
| 45 |
- false
|
| 46 |
+
- - progress
|
| 47 |
+
- false
|
| 48 |
- - pruner
|
| 49 |
- median
|
| 50 |
- - sampler
|
|
|
|
| 54 |
- - save_replay_buffer
|
| 55 |
- false
|
| 56 |
- - seed
|
| 57 |
+
- 4
|
| 58 |
- - storage
|
| 59 |
- null
|
| 60 |
- - study_name
|
| 61 |
- null
|
| 62 |
- - tensorboard_log
|
| 63 |
+
- runs/seals/Humanoid-v0__ppo__4__1672507667
|
| 64 |
- - track
|
| 65 |
- true
|
| 66 |
- - trained_agent
|
|
|
|
| 74 |
- - verbose
|
| 75 |
- 1
|
| 76 |
- - wandb_entity
|
| 77 |
+
- ernestum
|
| 78 |
- - wandb_project_name
|
| 79 |
+
- seals-experts-normalized
|
| 80 |
+
- - yaml_file
|
| 81 |
+
- null
|
config.yml
CHANGED
|
@@ -22,10 +22,20 @@
|
|
| 22 |
- - n_timesteps
|
| 23 |
- 10000000.0
|
| 24 |
- - normalize
|
| 25 |
-
-
|
|
|
|
|
|
|
| 26 |
- - policy
|
| 27 |
- MlpPolicy
|
| 28 |
- - policy_kwargs
|
| 29 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
- - vf_coef
|
| 31 |
- 0.819262464558427
|
|
|
|
| 22 |
- - n_timesteps
|
| 23 |
- 10000000.0
|
| 24 |
- - normalize
|
| 25 |
+
- gamma: 0.999
|
| 26 |
+
norm_obs: false
|
| 27 |
+
norm_reward: true
|
| 28 |
- - policy
|
| 29 |
- MlpPolicy
|
| 30 |
- - policy_kwargs
|
| 31 |
+
- activation_fn: !!python/name:torch.nn.modules.activation.ReLU ''
|
| 32 |
+
features_extractor_class: !!python/name:imitation.policies.base.NormalizeFeaturesExtractor ''
|
| 33 |
+
net_arch:
|
| 34 |
+
- pi:
|
| 35 |
+
- 256
|
| 36 |
+
- 256
|
| 37 |
+
vf:
|
| 38 |
+
- 256
|
| 39 |
+
- 256
|
| 40 |
- - vf_coef
|
| 41 |
- 0.819262464558427
|
ppo-seals-Humanoid-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:fc73fd0755a1de9e7bee9a436c0cefff3ba002b99cd9e03ebf6b26eed3422f3b
|
| 3 |
+
size 4024138
|
ppo-seals-Humanoid-v0/_stable_baselines3_version
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
1.6.
|
|
|
|
| 1 |
+
1.6.2
|
ppo-seals-Humanoid-v0/data
CHANGED
|
@@ -4,24 +4,24 @@
|
|
| 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": {
|
| 23 |
":type:": "<class 'dict'>",
|
| 24 |
-
":serialized:": "
|
| 25 |
"activation_fn": "<class 'torch.nn.modules.activation.ReLU'>",
|
| 26 |
"net_arch": [
|
| 27 |
{
|
|
@@ -34,7 +34,8 @@
|
|
| 34 |
256
|
| 35 |
]
|
| 36 |
}
|
| 37 |
-
]
|
|
|
|
| 38 |
},
|
| 39 |
"observation_space": {
|
| 40 |
":type:": "<class 'gym.spaces.box.Box'>",
|
|
@@ -51,7 +52,7 @@
|
|
| 51 |
},
|
| 52 |
"action_space": {
|
| 53 |
":type:": "<class 'gym.spaces.box.Box'>",
|
| 54 |
-
":serialized:": "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
|
| 55 |
"dtype": "float32",
|
| 56 |
"_shape": [
|
| 57 |
17
|
|
@@ -66,17 +67,17 @@
|
|
| 66 |
"num_timesteps": 10000384,
|
| 67 |
"_total_timesteps": 10000000,
|
| 68 |
"_num_timesteps_at_start": 0,
|
| 69 |
-
"seed":
|
| 70 |
"action_noise": null,
|
| 71 |
-
"start_time":
|
| 72 |
"learning_rate": {
|
| 73 |
":type:": "<class 'function'>",
|
| 74 |
-
":serialized:": "
|
| 75 |
},
|
| 76 |
-
"tensorboard_log": "runs/seals/Humanoid-
|
| 77 |
"lr_schedule": {
|
| 78 |
":type:": "<class 'function'>",
|
| 79 |
-
":serialized:": "
|
| 80 |
},
|
| 81 |
"_last_obs": null,
|
| 82 |
"_last_episode_starts": {
|
|
@@ -85,7 +86,7 @@
|
|
| 85 |
},
|
| 86 |
"_last_original_obs": {
|
| 87 |
":type:": "<class 'numpy.ndarray'>",
|
| 88 |
-
":serialized:": "
|
| 89 |
},
|
| 90 |
"_episode_num": 0,
|
| 91 |
"use_sde": false,
|
|
@@ -93,7 +94,7 @@
|
|
| 93 |
"_current_progress_remaining": -3.8399999999993994e-05,
|
| 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 +111,7 @@
|
|
| 110 |
"n_epochs": 20,
|
| 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 0x7f9616b2a790>",
|
| 8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f9616b2a820>",
|
| 9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f9616b2a8b0>",
|
| 10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f9616b2a940>",
|
| 11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f9616b2a9d0>",
|
| 12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f9616b2aa60>",
|
| 13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f9616b2aaf0>",
|
| 14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f9616b2ab80>",
|
| 15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f9616b2ac10>",
|
| 16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f9616b2aca0>",
|
| 17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f9616b2ad30>",
|
| 18 |
"__abstractmethods__": "frozenset()",
|
| 19 |
+
"_abc_impl": "<_abc_data object at 0x7f9616b22c60>"
|
| 20 |
},
|
| 21 |
"verbose": 1,
|
| 22 |
"policy_kwargs": {
|
| 23 |
":type:": "<class 'dict'>",
|
| 24 |
+
":serialized:": "gAWVwAAAAAAAAAB9lCiMDWFjdGl2YXRpb25fZm6UjBt0b3JjaC5ubi5tb2R1bGVzLmFjdGl2YXRpb26UjARSZUxVlJOUjAhuZXRfYXJjaJRdlH2UKIwCcGmUXZQoTQABTQABZYwCdmaUXZQoTQABTQABZXVhjBhmZWF0dXJlc19leHRyYWN0b3JfY2xhc3OUjBdpbWl0YXRpb24ucG9saWNpZXMuYmFzZZSMGk5vcm1hbGl6ZUZlYXR1cmVzRXh0cmFjdG9ylJOUdS4=",
|
| 25 |
"activation_fn": "<class 'torch.nn.modules.activation.ReLU'>",
|
| 26 |
"net_arch": [
|
| 27 |
{
|
|
|
|
| 34 |
256
|
| 35 |
]
|
| 36 |
}
|
| 37 |
+
],
|
| 38 |
+
"features_extractor_class": "<class 'imitation.policies.base.NormalizeFeaturesExtractor'>"
|
| 39 |
},
|
| 40 |
"observation_space": {
|
| 41 |
":type:": "<class 'gym.spaces.box.Box'>",
|
|
|
|
| 52 |
},
|
| 53 |
"action_space": {
|
| 54 |
":type:": "<class 'gym.spaces.box.Box'>",
|
| 55 |
+
":serialized:": "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",
|
| 56 |
"dtype": "float32",
|
| 57 |
"_shape": [
|
| 58 |
17
|
|
|
|
| 67 |
"num_timesteps": 10000384,
|
| 68 |
"_total_timesteps": 10000000,
|
| 69 |
"_num_timesteps_at_start": 0,
|
| 70 |
+
"seed": 8,
|
| 71 |
"action_noise": null,
|
| 72 |
+
"start_time": 1672507673181022961,
|
| 73 |
"learning_rate": {
|
| 74 |
":type:": "<class 'function'>",
|
| 75 |
+
":serialized:": "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"
|
| 76 |
},
|
| 77 |
+
"tensorboard_log": "runs/seals/Humanoid-v0__ppo__4__1672507667/seals-Humanoid-v0",
|
| 78 |
"lr_schedule": {
|
| 79 |
":type:": "<class 'function'>",
|
| 80 |
+
":serialized:": "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"
|
| 81 |
},
|
| 82 |
"_last_obs": null,
|
| 83 |
"_last_episode_starts": {
|
|
|
|
| 86 |
},
|
| 87 |
"_last_original_obs": {
|
| 88 |
":type:": "<class 'numpy.ndarray'>",
|
| 89 |
+
":serialized:": "gAWVRgwAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJbQCwAAAAAAADizaI4b13Q/9G/82KQjdT+c/9pht1/2P9hzqA2+/+8/Yypi628Wb7+PFus/6yh1P2mI75EZIHM/IPtMp+EgXj9sGPaJjg56v+Y8yfGRF3w/2LKs7N7LcD+OI89C/yF+P76gc4Hpu3+/ob+dwZO2eL9A0y7weyFIP2y/VahVn2K/KMKYGIRPZz8p66BbCKWAv4D9LJeFHRk/fDjtrJ7Ua7+aEn4xUu5jv2aCJXkMSHq/swl2uyDjgb/QLMqe3dtzPzFeJjzQrXG/Hwicc1Vqf7/8UGFVAY1jP+JD6lqnLWm/DloA1YPKgb/0nCeLY3tpPwni5BadtYO/MHqqraJ5YL9oQgiNe3Bcv9VNZfh/D4I/Hn4h/aqmcz8YZV66ck1hv2xiliDh4oG/0qlCLIe5dL9qjmhElO2Cv7ZEx3abG4C/sHJXEcWoX78DwqZZhOp1v94JzsEFAXA/aAcyOUZGgr9WTCNbjJt5P4L8PYZMA3I/TR01aq/Wc78AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAANj2JkKD2wFAdxOvyUvIAUCH8q+1QRaiPz4VU4D2UzM/sHWdYwOcrj/ab1aFeo+Av5KkFQROgMC/HrNeulp3jT/z/Q4JY50QQMOO3ofnpCBAPUjXEhp8tj9UfVaoQOS1P2hWsE3ixIE/MK1rWGLo4D4zUKeaY1OFP9GLbqtnizI/QX6EPKnPqr+a5Y0ndwpVvx2XdPqh6Nk//T2EXThJAEAhy3nd4bOmP7z31wXv0aU/BErCEzyMqT/kia12FPosv1TlQArXgoI/Ycw7pprpMj+bXHy3DCDRv4bv+uq+7YC/mdIZRllOyT8cGW4GQWkXQIRlzOvWfs8/QkeB+1V9yj/+4sNkaY6qP7DMQ4O0A4S/q2YJ47C/kb/rMJ4yUwWzv9M776LHHbq/WJ1eB9Sv27+jzRxMiX7pv3vwbGsrGhJAVBqeOXfm6z8tjU/Ut0LrP7EQ3afJsJk/QchZua91cr+m6Ib1lcOcv1SJzNKsy8C/oG8756Pbqb9Ys6BhyxDOvzJ9is6ai/e/b7tbPFkPBUB0nU6W2JLwP5h/fkZ7XPA/qGw2OJ3Xkj+faq5u8CJnv/PDYzPRy5i/aehEUHllvr/CHNrLrlWgv0Im6AYeBsS/CEhC+NV19b+7ssy+Okb8Px9m+SjKTc8/wuNBFfKhyj++TSpoUxeqPyV9Hg+56YY/SdmXmT98lb9n4GGR3KayP7UZZFZanL6/Bjo1lfAX2z+BlCOtV4Tpv3vwbGsrGhJAJpinPRzm6z/rGQ5HOk/rP5sA0ICdHZo/g8+KlTHleT+7hkOieamkvwLc0dcDk8A/KjYLQwtlsr8CI00PCKbNP1XtrfWPjfe/b7tbPFkPBUCl3G2Xw5PwP3Nk2G8RYvA/IycGqHl5kz9+OqWQqDVyP2bhaXUMtaO/1tGtEZYdvj8rpKZGXPWpv6jqBfGM1cM/8HCDJSV39b+7ssy+Okb8P8yxqN+tn9o/zGFN9oPQ1D+GHQM/14O9PxrfwQdE+p8/PA91b11Upr/OnsIs4bXFPx7s5D+i3bs/ClyiV45Q2b+qAvzAeGzmP2z8deREgfk/zgLDabco1D9stgY4DdPVP3rkJeCvqMU/6rPhkykusz+Z9q90HZ/Dv3xQjyPiZ78/0WsX0X9i1T9Tq7fJfSbSv7sbOXPgIeE/w96z2Gks8z/tIQctJW/aP6MqnUUKctQ/dfuzfLndvT+LNEeO492ev1SnFVXq6qS/GpY6qpfExb+/WiRpvIO6P1Wm+cyzmNk/cRJnChI85j9s/HXkRIH5P+7NUdloMtQ/t2NKdnaJ1T+vkWY3H4vFP3Zp8jtrOrO/Aq+DUTFDw7/36emcGtK/vyUqDZTyC9U/HBpRk6N00j9yyGfnwRHhP8Pes9hpLPM/AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA/FS45AU/aL/jcWC8tsyBvyGlaA0QR2o/sNhPaTNFNb8X4SIyX2aCv+db5QROi2Q/qQn7yMuOaL9+AqkrYBGGv0/VAXBTN3q/eoBSrLC2LT/aD8uUO+2Cv/4W9eK8+2Q//tURn2Njc78YaJ1QnBuGv4ZBGeyRPnq/STEe/qEOLj/bTt4+I2eDv23yXY62+GQ/UbY121rQcD/bKHm6g0OKv5Vms0bL6lm/LZJVPOXIMb8emcrAdUWDvySM4rubtGw/PrWQGOAlcD9eNZsD6cJwv6LLS5w/blm/ARAqbfSUaT+8Fuy0/CODv6I/NuIPJWs/PrWQGOAlcD9eNZsD6cJwv6LLS5w/blm/ARAqbfSUaT+8Fuy0/CODv6I/NuIPJWs/0A06uN/nOT8kricdMwmTv0IjFZaaemc/yMjOGwP5UT8IrUUAF/aCv4uusdR3hmI/O7IEe8MxOD802uDEsg6Rv64HDt/cdGc/VK8cDgdKXj8ntb2EzPCCv4dHr4mBIWI/O7IEe8MxOD802uDEsg6Rv64HDt/cdGc/VK8cDgdKXj8ntb2EzPCCv4dHr4mBIWI/Zmmg9erMfb/AEsVcYQGMv5V+GibUsG8/Gp7HuuCoYT9ExwazGvuGv9kT/vsVH14/7J4i8JhPfr/MyUgWLV1+v3v1gMD9YGS/wmwp8MtlYj8ZqVBMZuKEv2ZiXACqTmc/n64lwuMhYj/ogrCwdXCAv53rOQxVA4I/eO9iukMmMz/xvWJ4SoF5v0dbzqDDXFo/mfuLKF9NYj9BkikZz6tyv4Ota2ae74g/PlXnhRqzND8mujH0LsB7v7F080rhyWE/AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAJSMBW51bXB5lIwFZHR5cGWUk5SMAmY4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAU16AYaUjAFDlHSUUpQu"
|
| 90 |
},
|
| 91 |
"_episode_num": 0,
|
| 92 |
"use_sde": false,
|
|
|
|
| 94 |
"_current_progress_remaining": -3.8399999999993994e-05,
|
| 95 |
"ep_info_buffer": {
|
| 96 |
":type:": "<class 'collections.deque'>",
|
| 97 |
+
":serialized:": "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"
|
| 98 |
},
|
| 99 |
"ep_success_buffer": {
|
| 100 |
":type:": "<class 'collections.deque'>",
|
|
|
|
| 111 |
"n_epochs": 20,
|
| 112 |
"clip_range": {
|
| 113 |
":type:": "<class 'function'>",
|
| 114 |
+
":serialized:": "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"
|
| 115 |
},
|
| 116 |
"clip_range_vf": null,
|
| 117 |
"normalize_advantage": true,
|
ppo-seals-Humanoid-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 sha256:13f2895ca27820a114ef88d97804ff78cb19695f8f8ba161cd9275ff27332f96
|
| 3 |
+
size 2652208
|
ppo-seals-Humanoid-v0/policy.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:d773dfed02e72f8b59472a95a3d7071678e322a3b599a141914a4e8a76a47051
|
| 3 |
+
size 1329333
|
ppo-seals-Humanoid-v0/system_info.txt
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
-
OS: Linux-5.4.0-
|
| 2 |
Python: 3.8.10
|
| 3 |
-
Stable-Baselines3: 1.6.
|
| 4 |
PyTorch: 1.11.0+cu102
|
| 5 |
GPU Enabled: False
|
| 6 |
Numpy: 1.22.3
|
|
|
|
| 1 |
+
OS: Linux-5.4.0-125-generic-x86_64-with-glibc2.29 #141-Ubuntu SMP Wed Aug 10 13:42:03 UTC 2022
|
| 2 |
Python: 3.8.10
|
| 3 |
+
Stable-Baselines3: 1.6.2
|
| 4 |
PyTorch: 1.11.0+cu102
|
| 5 |
GPU Enabled: False
|
| 6 |
Numpy: 1.22.3
|
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:b072c59a62891f0ea277136d303d4e7b4f90002db3217c17179cc493938d4c7d
|
| 3 |
+
size 1904784
|
results.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"mean_reward":
|
|
|
|
| 1 |
+
{"mean_reward": 2242.5097121999997, "std_reward": 858.2038158853227, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-02T10:55:01.214765"}
|
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:f344df233dd2942398271be5fb358e49a601ffaca899d5e02b62f09ec0863eac
|
| 3 |
+
size 340699
|
vec_normalize.pkl
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 sha256:8aae0810e8d965c2ae992353c43e7d8f0ccee57070a220890cb4779a271a28ff
|
| 3 |
+
size 13864
|