Initial commit
Browse files- README.md +12 -4
- args.yml +11 -5
- config.yml +5 -1
- replay.mp4 +2 -2
- results.json +1 -1
- sac-seals-Humanoid-v0.zip +2 -2
- sac-seals-Humanoid-v0/_stable_baselines3_version +1 -1
- sac-seals-Humanoid-v0/actor.optimizer.pth +1 -1
- sac-seals-Humanoid-v0/critic.optimizer.pth +1 -1
- sac-seals-Humanoid-v0/data +27 -25
- sac-seals-Humanoid-v0/ent_coef_optimizer.pth +2 -2
- sac-seals-Humanoid-v0/policy.pth +1 -1
- sac-seals-Humanoid-v0/pytorch_variables.pth +1 -1
- sac-seals-Humanoid-v0/system_info.txt +2 -2
- train_eval_metrics.zip +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 sac --env seals/Humanoid-v0 -f logs/
|
| 42 |
```
|
| 43 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
## Training (with the RL Zoo)
|
| 45 |
```
|
| 46 |
python train.py --algo sac --env seals/Humanoid-v0 -f logs/
|
| 47 |
# Upload the model and generate video (when possible)
|
| 48 |
-
python -m
|
| 49 |
```
|
| 50 |
|
| 51 |
## Hyperparameters
|
|
@@ -58,7 +64,9 @@ OrderedDict([('batch_size', 64),
|
|
| 58 |
('n_timesteps', 2000000.0),
|
| 59 |
('policy', 'MlpPolicy'),
|
| 60 |
('policy_kwargs',
|
| 61 |
-
'
|
|
|
|
|
|
|
| 62 |
('tau', 0.08),
|
| 63 |
('train_freq', 8),
|
| 64 |
('normalize', False)])
|
|
|
|
| 10 |
results:
|
| 11 |
- metrics:
|
| 12 |
- type: mean_reward
|
| 13 |
+
value: 423.21 +/- 100.55
|
| 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 sac --env seals/Humanoid-v0 -orga HumanCompatibleAI -f logs/
|
| 41 |
python enjoy.py --algo sac --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 sac --env seals/Humanoid-v0 -orga HumanCompatibleAI -f logs/
|
| 47 |
+
rl_zoo3 enjoy --algo sac --env seals/Humanoid-v0 -f logs/
|
| 48 |
+
```
|
| 49 |
+
|
| 50 |
## Training (with the RL Zoo)
|
| 51 |
```
|
| 52 |
python train.py --algo sac --env seals/Humanoid-v0 -f logs/
|
| 53 |
# Upload the model and generate video (when possible)
|
| 54 |
+
python -m rl_zoo3.push_to_hub --algo sac --env seals/Humanoid-v0 -f logs/ -orga HumanCompatibleAI
|
| 55 |
```
|
| 56 |
|
| 57 |
## Hyperparameters
|
|
|
|
| 64 |
('n_timesteps', 2000000.0),
|
| 65 |
('policy', 'MlpPolicy'),
|
| 66 |
('policy_kwargs',
|
| 67 |
+
{'log_std_init': -0.1034412732183072,
|
| 68 |
+
'net_arch': [400, 300],
|
| 69 |
+
'use_sde': False}),
|
| 70 |
('tau', 0.08),
|
| 71 |
('train_freq', 8),
|
| 72 |
('normalize', False)])
|
args.yml
CHANGED
|
@@ -1,6 +1,8 @@
|
|
| 1 |
!!python/object/apply:collections.OrderedDict
|
| 2 |
- - - algo
|
| 3 |
- sac
|
|
|
|
|
|
|
| 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 |
- sac
|
| 4 |
+
- - conf_file
|
| 5 |
+
- hyperparams/python/sac.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 |
+
- 9
|
| 58 |
- - storage
|
| 59 |
- null
|
| 60 |
- - study_name
|
| 61 |
- null
|
| 62 |
- - tensorboard_log
|
| 63 |
+
- runs/seals/Humanoid-v0__sac__9__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
|
@@ -14,7 +14,11 @@
|
|
| 14 |
- - policy
|
| 15 |
- MlpPolicy
|
| 16 |
- - policy_kwargs
|
| 17 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
- - tau
|
| 19 |
- 0.08
|
| 20 |
- - train_freq
|
|
|
|
| 14 |
- - policy
|
| 15 |
- MlpPolicy
|
| 16 |
- - policy_kwargs
|
| 17 |
+
- log_std_init: -0.1034412732183072
|
| 18 |
+
net_arch:
|
| 19 |
+
- 400
|
| 20 |
+
- 300
|
| 21 |
+
use_sde: false
|
| 22 |
- - tau
|
| 23 |
- 0.08
|
| 24 |
- - train_freq
|
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 sha256:7639bb0e809f778cd3645ad0f5bd61b656fc16e6ff4091aa6d72efd33071b754
|
| 3 |
+
size 743877
|
results.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"mean_reward":
|
|
|
|
| 1 |
+
{"mean_reward": 423.20559890000004, "std_reward": 100.54795464840286, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-02T10:56:36.878584"}
|
sac-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 sha256:8cc462f534b854735d09fb4a87b18d3c4b5af055b83429cde41630f31dd9f101
|
| 3 |
+
size 12383521
|
sac-seals-Humanoid-v0/_stable_baselines3_version
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
1.6.
|
|
|
|
| 1 |
+
1.6.2
|
sac-seals-Humanoid-v0/actor.optimizer.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2263133
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eb5fa7fb509bb77443ffa59e82cf569d7c2808bdfe8e08500aa17ebd93069ed6
|
| 3 |
size 2263133
|
sac-seals-Humanoid-v0/critic.optimizer.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4472889
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3896df66f6ab533f84b17651fa7791dea19f5c7569250f0d289819e5cf08415a
|
| 3 |
size 4472889
|
sac-seals-Humanoid-v0/data
CHANGED
|
@@ -4,17 +4,17 @@
|
|
| 4 |
":serialized:": "gAWVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLnNhYy5wb2xpY2llc5SMCVNBQ1BvbGljeZSTlC4=",
|
| 5 |
"__module__": "stable_baselines3.sac.policies",
|
| 6 |
"__doc__": "\n Policy class (with both actor and critic) for SAC.\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 use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\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()`` when using gSDE 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 clip_mean: Clip the mean output when using gSDE to avoid numerical instability.\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 :param n_critics: Number of critic networks to create.\n :param share_features_extractor: Whether to share or not the features extractor\n between the actor and the critic (this saves computation time)\n ",
|
| 7 |
-
"__init__": "<function SACPolicy.__init__ at
|
| 8 |
-
"_build": "<function SACPolicy._build at
|
| 9 |
-
"_get_constructor_parameters": "<function SACPolicy._get_constructor_parameters at
|
| 10 |
-
"reset_noise": "<function SACPolicy.reset_noise at
|
| 11 |
-
"make_actor": "<function SACPolicy.make_actor at
|
| 12 |
-
"make_critic": "<function SACPolicy.make_critic at
|
| 13 |
-
"forward": "<function SACPolicy.forward at
|
| 14 |
-
"_predict": "<function SACPolicy._predict at
|
| 15 |
-
"set_training_mode": "<function SACPolicy.set_training_mode at
|
| 16 |
"__abstractmethods__": "frozenset()",
|
| 17 |
-
"_abc_impl": "<_abc_data object at
|
| 18 |
},
|
| 19 |
"verbose": 1,
|
| 20 |
"policy_kwargs": {
|
|
@@ -40,7 +40,7 @@
|
|
| 40 |
},
|
| 41 |
"action_space": {
|
| 42 |
":type:": "<class 'gym.spaces.box.Box'>",
|
| 43 |
-
":serialized:": "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
|
| 44 |
"dtype": "float32",
|
| 45 |
"_shape": [
|
| 46 |
17
|
|
@@ -55,17 +55,17 @@
|
|
| 55 |
"num_timesteps": 2000000,
|
| 56 |
"_total_timesteps": 2000000,
|
| 57 |
"_num_timesteps_at_start": 0,
|
| 58 |
-
"seed":
|
| 59 |
"action_noise": null,
|
| 60 |
-
"start_time":
|
| 61 |
"learning_rate": {
|
| 62 |
":type:": "<class 'function'>",
|
| 63 |
-
":serialized:": "
|
| 64 |
},
|
| 65 |
-
"tensorboard_log": "runs/seals/Humanoid-
|
| 66 |
"lr_schedule": {
|
| 67 |
":type:": "<class 'function'>",
|
| 68 |
-
":serialized:": "
|
| 69 |
},
|
| 70 |
"_last_obs": null,
|
| 71 |
"_last_episode_starts": {
|
|
@@ -74,7 +74,7 @@
|
|
| 74 |
},
|
| 75 |
"_last_original_obs": {
|
| 76 |
":type:": "<class 'numpy.ndarray'>",
|
| 77 |
-
":serialized:": "
|
| 78 |
},
|
| 79 |
"_episode_num": 2000,
|
| 80 |
"use_sde": false,
|
|
@@ -82,7 +82,7 @@
|
|
| 82 |
"_current_progress_remaining": 0.0,
|
| 83 |
"ep_info_buffer": {
|
| 84 |
":type:": "<class 'collections.deque'>",
|
| 85 |
-
":serialized:": "gAWVgRAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////
|
| 86 |
},
|
| 87 |
"ep_success_buffer": {
|
| 88 |
":type:": "<class 'collections.deque'>",
|
|
@@ -100,13 +100,13 @@
|
|
| 100 |
":type:": "<class 'abc.ABCMeta'>",
|
| 101 |
":serialized:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
|
| 102 |
"__module__": "stable_baselines3.common.buffers",
|
| 103 |
-
"__doc__": "\n Replay buffer used in off-policy algorithms like SAC/TD3.\n\n :param buffer_size: Max number of element in the buffer\n :param observation_space: Observation space\n :param action_space: Action space\n :param device
|
| 104 |
-
"__init__": "<function ReplayBuffer.__init__ at
|
| 105 |
-
"add": "<function ReplayBuffer.add at
|
| 106 |
-
"sample": "<function ReplayBuffer.sample at
|
| 107 |
-
"_get_samples": "<function ReplayBuffer._get_samples at
|
| 108 |
"__abstractmethods__": "frozenset()",
|
| 109 |
-
"_abc_impl": "<_abc_data object at
|
| 110 |
},
|
| 111 |
"replay_buffer_kwargs": {},
|
| 112 |
"train_freq": {
|
|
@@ -116,5 +116,7 @@
|
|
| 116 |
"use_sde_at_warmup": false,
|
| 117 |
"target_entropy": -17.0,
|
| 118 |
"ent_coef": "auto",
|
| 119 |
-
"target_update_interval": 1
|
|
|
|
|
|
|
| 120 |
}
|
|
|
|
| 4 |
":serialized:": "gAWVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLnNhYy5wb2xpY2llc5SMCVNBQ1BvbGljeZSTlC4=",
|
| 5 |
"__module__": "stable_baselines3.sac.policies",
|
| 6 |
"__doc__": "\n Policy class (with both actor and critic) for SAC.\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 use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\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()`` when using gSDE 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 clip_mean: Clip the mean output when using gSDE to avoid numerical instability.\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 :param n_critics: Number of critic networks to create.\n :param share_features_extractor: Whether to share or not the features extractor\n between the actor and the critic (this saves computation time)\n ",
|
| 7 |
+
"__init__": "<function SACPolicy.__init__ at 0x7f094c04dee0>",
|
| 8 |
+
"_build": "<function SACPolicy._build at 0x7f094c04df70>",
|
| 9 |
+
"_get_constructor_parameters": "<function SACPolicy._get_constructor_parameters at 0x7f094bfd6040>",
|
| 10 |
+
"reset_noise": "<function SACPolicy.reset_noise at 0x7f094bfd60d0>",
|
| 11 |
+
"make_actor": "<function SACPolicy.make_actor at 0x7f094bfd6160>",
|
| 12 |
+
"make_critic": "<function SACPolicy.make_critic at 0x7f094bfd61f0>",
|
| 13 |
+
"forward": "<function SACPolicy.forward at 0x7f094bfd6280>",
|
| 14 |
+
"_predict": "<function SACPolicy._predict at 0x7f094bfd6310>",
|
| 15 |
+
"set_training_mode": "<function SACPolicy.set_training_mode at 0x7f094bfd63a0>",
|
| 16 |
"__abstractmethods__": "frozenset()",
|
| 17 |
+
"_abc_impl": "<_abc_data object at 0x7f094c04ccc0>"
|
| 18 |
},
|
| 19 |
"verbose": 1,
|
| 20 |
"policy_kwargs": {
|
|
|
|
| 40 |
},
|
| 41 |
"action_space": {
|
| 42 |
":type:": "<class 'gym.spaces.box.Box'>",
|
| 43 |
+
":serialized:": "gAWVgQwAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLEYWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWRAAAAAAAAADNzMy+zczMvs3MzL7NzMy+zczMvs3MzL7NzMy+zczMvs3MzL7NzMy+zczMvs3MzL7NzMy+zczMvs3MzL7NzMy+zczMvpRoCksRhZSMAUOUdJRSlIwEaGlnaJRoEiiWRAAAAAAAAADNzMw+zczMPs3MzD7NzMw+zczMPs3MzD7NzMw+zczMPs3MzD7NzMw+zczMPs3MzD7NzMw+zczMPs3MzD7NzMw+zczMPpRoCksRhZRoFXSUUpSMDWJvdW5kZWRfYmVsb3eUaBIolhEAAAAAAAAAAQEBAQEBAQEBAQEBAQEBAQGUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLEYWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYRAAAAAAAAAAEBAQEBAQEBAQEBAQEBAQEBlGghSxGFlGgVdJRSlIwKX25wX3JhbmRvbZSMFG51bXB5LnJhbmRvbS5fcGlja2xllIwSX19yYW5kb21zdGF0ZV9jdG9ylJOUjAdNVDE5OTM3lIWUUpR9lCiMDWJpdF9nZW5lcmF0b3KUaDCMBXN0YXRllH2UKIwDa2V5lGgSKJbACQAAAAAAAAAAAICWR4dW2nD4c9/tiD9yYQ5UOve/7nXhzaP9+vAxRRXodL2vC07Qfea8Q7YKIAr6iJY63fvVCljH2w97/zNxhBcWHKA2zKTgZ5bu9v8YY5SoITEA1VoQPXW4FUlQoEin0WsSEEzTAvpEyz73ckUSH613mxt5/ErHc38ZhBxPJ3W6TwkrI1XsTCQcYP02bKbSWxpmmex3QluSxwW/36vVmlw7ODOYTtk/Uk4U0fA0akVQ9SCMK3c1Xu/BCghERTGKwlhve0FL21w4icEwDRl0WJvIwts9JzZpoZ0r9v/W/pfR4GqJP+tuDTbMZ8D78eCPldHUFW3orfAuzaCuQV27Tjd+GWUytFCMA1WtrFLbGaTtd9emacXMhDqqC0XqR6NYdB47IDs6TtiTep2osMPn4y7HUCah8WWxAJKTzvo5GM76PGLP23miUh+G9m6svcUKBmLglfYVeksj8aOeOZnn7FfzQ1B2OIEy1WVOmLGW6PH779zK/ybasJ3Vmo3frEcGh390M2fUnYGcZsV3BkZocLzHZN3k4IdP9e15NE3pgeIEh1f7/QNuMHFej1IqajFdWqBsODbsS31CazisIwVNUXkMEsYDaSQAs83RmDWZC1lHWYhE7ROz6vn+lCIaRRLbzUO+mXfPfrg+twBQJ+P90TQuxJRvnZkE043DvrDDqwng7EsD/mthfp6xnQ2NWDse/XGnohHAtoL0Ut8oDu3/+jLA4QUGQ2dfWLvRt1QDE2njs2JaAhsBPzwy8oza2P1cun9SpjT8YpgK5HRIj2YMGoH5+PPWfv/3pE4m6Lu5S3tpGJkBljZ6QyM9NSobvrWuFUek7XJ0h/P4nJqwiaP6KsRAw7U5deVAFGEu1NWesKqL5Vt8miGAMX4pk2vghojcNf9+9+Gf8fWD18pE/cz1otQEvjJ6auVzkAgNJ3gmeSXWC1VBVT4imQLt/cejUhPiNM8/mbiJ3Utgwt8wpqLaA8xrPxfftRaxkQSxh3qUXoL/To7HYO+WFi6/gZoew7VXhLmzGB2/hy6+Xe2emdVPNfInKWLG6vTN+xJybi3SMzvxVPULHYEz4yciJxRX9GM4gdQQbIl0UA39RU8o9J7otzJ8IpWJY71kwofBgxzdJhVg3UJES4cFKHogpPKLqv231DuvoMW0Frp+OSO9/f/RueALgbyfT4nmxHpfpkowsw/+667vhL5mc8ieM0N5W6RoyXYy96wqs1qwkhMaGqi+NMqVImue1lPiap/gbAN8KF4JKcYOdfq0swL8js5ix9mtP6apwY2vP3HjznmqJvLdwAmJoS0M1lUt86bZr5FDNov6NPLjvbZ43s6E4nthjAs9SnXt2zpG1DObUGkcAC60vKnxYu0rBEdPfFs1dEs3g+b5Urcne/PWW8j8B6zTXNy9NmisZQZTWUSFhJTBzmERMb3yMwYzrsTt679vkuy0tdQ2BQb3vr7iSQPYnGqnI/xkARj1tdQrNRUZaIxtP93zC08RZlL1WYvKTNW3sPL3bVCW/zIJNBUnmu7YYahDPEVeOA+M8YrXc9slu3RkRUg7bXnHcMFfuj2g0jxMgiEwvp0yISF4aa25TCWaY9dGAZhQZD+IZXvTz9Wk2ayDt4dVIt4ab72GMsyROJu5wxHM6VsKTnPFMnhwNiBgtmGZzDW3CAsuX9W0wcAKRL04oZj+z9k/BJVYsWPagmO8++yejQMlbTCcjeIDx++NcqiRv8wa/P0WIJZIKPJ7q/HhY/lid6EHBq+LzSCX0TFg+ujCfOhUovQRfHUO+fDN96ah3hkyk5m3wEWf2Gu7fAM75H7XIJzH92ubHP8Ls6MjwmxntptTNs/NLD+pdYLOFgHkmlMTeCcERp/MV9RDuWYZqmOGDPhOHK9Iw/8E7vJ80xBO068021RpCy+OgmFkjn2EAAVhxTrf9XKbmxbVjSKvpy87zehLeWM9VB5PVhdtG+jwI8ZZNpbH+Bi7Oe8QwhYEbktHgywd3xD6PmW1SAjix/GSvgDQ1VedqhQsC2t3lzuWrQTcQxY9rZ4a3P89DaGLcZFRi1BEywIsEuU7h0lPo2TfiLvzjiD1v8yYHRYwc/y08pDgpCXT5OUG5AfnIQ93I9LxzZnAkhWWKmI5elZKL4kEQAemuLwH+dBeDgJ/TlgXGquP7CJ5teLwDXTDKWO+PNW3vsN/MIFIeidhRItD2crkDGb47YQKu0BINGvY6wxfgoAjtjwVBhfBPZNq0IG9T9AcxhIpnlUsA9cezFu4yFgvRCGK1L5mp6snqou1YMrk4Qclrcak4uw4JNDJaoBlAb7FrC3ZNF8tHAItc8j/dGTGS3u3RCHDYdiIycz2EdguhwCqz/F9lToY+APSceGnXqGtwI5UE1cryWm373d/WOFG4VNAuhTXO22qBzgfM5SfaY8eyp8Zi9+3+Wh/5F5GGcQ2SimAhgq+JpgouRo9viEP1PGdElzPNnXh6PNuexia+2sTsaeDZ4fy79OxnQaK1JfWYqr+1Pz87O0TMwOg1FOFnCsTgJDxUNHSlS2JFhlP0S71oUQ3mAPo8K0pKLLHYnSiZ5xow9JcHE6trA3jFU0MeIJxrYLI29TAfz/ek1Q4yEVeptrzzQhpuOKFjDtw/kFvXUStQY3r96tLQ8SecKEflEBeWL71jIp43HSuJnpHJnwPlJvT5aBfVRRA1raMgN1LH8lLKbHt8f3cjvNgonP5r68dfaF/pefUjLUKkVaGDoGpLrFUYIuuCSZGWx/3S2DrSu/lW7UCUH5qYYB9eM1q6k+x7u9XQly0dugfE2TRc4lEGuh7Z8LbNsnm9ZNV4ooOLN8fV7B5KdzgDR4v3jsFYZ1bk7sG3nda5lwxSIM2lHujaPPWK2ue1fJ3cLG8SCeOPKnSZeOhu1b7yHghfyeea+JX3UG5kAihCsL4gX2/lZ4g4VDXTOc6NDFha92SmVFIpgcTfpXRjyZki9TrrNvPKfexbnqpbi6PG2SHWoe2DTUUrowOlhhDqIIswnn+YEviyijFNHNjrGUxkdWqeZeNdEMi2CQRawxp14E19CHV5/2VhFbYpvoqlPDfnBVcNSF0B3dzf0zNuVCd3ARBPJVcqJCorcV+VcOYzUa+Lqroeb4gVrkBnxkomXfMxYjzVDr+EMDPgL9q6Kbl9sY08lAVs1l2Twp5p7RFIK82vVZXRE9lwcWOdU9esRxTWKrygc+BYQYtIwZffRv/9FEWM5DuXKfM9J9AaY7T2McwQV8mrGZM9RYHA7ZV+rIufnyqbZea6n9Min8s0zL+xj1GLZq4SESxXJY0x+mZETcy1kctTRwsQ21u5F03NJjvbjpryJRoB4wCdTSUiYiHlFKUKEsDaAtOTk5K/////0r/////SwB0lGJNcAKFlGgVdJRSlIwDcG9zlE1wAnWMCWhhc19nYXVzc5RLAIwFZ2F1c3OURwAAAAAAAAAAdWJ1Yi4=",
|
| 44 |
"dtype": "float32",
|
| 45 |
"_shape": [
|
| 46 |
17
|
|
|
|
| 55 |
"num_timesteps": 2000000,
|
| 56 |
"_total_timesteps": 2000000,
|
| 57 |
"_num_timesteps_at_start": 0,
|
| 58 |
+
"seed": 10,
|
| 59 |
"action_noise": null,
|
| 60 |
+
"start_time": 1672507674041434876,
|
| 61 |
"learning_rate": {
|
| 62 |
":type:": "<class 'function'>",
|
| 63 |
+
":serialized:": "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"
|
| 64 |
},
|
| 65 |
+
"tensorboard_log": "runs/seals/Humanoid-v0__sac__9__1672507667/seals-Humanoid-v0",
|
| 66 |
"lr_schedule": {
|
| 67 |
":type:": "<class 'function'>",
|
| 68 |
+
":serialized:": "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"
|
| 69 |
},
|
| 70 |
"_last_obs": null,
|
| 71 |
"_last_episode_starts": {
|
|
|
|
| 74 |
},
|
| 75 |
"_last_original_obs": {
|
| 76 |
":type:": "<class 'numpy.ndarray'>",
|
| 77 |
+
":serialized:": "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"
|
| 78 |
},
|
| 79 |
"_episode_num": 2000,
|
| 80 |
"use_sde": false,
|
|
|
|
| 82 |
"_current_progress_remaining": 0.0,
|
| 83 |
"ep_info_buffer": {
|
| 84 |
":type:": "<class 'collections.deque'>",
|
| 85 |
+
":serialized:": "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"
|
| 86 |
},
|
| 87 |
"ep_success_buffer": {
|
| 88 |
":type:": "<class 'collections.deque'>",
|
|
|
|
| 100 |
":type:": "<class 'abc.ABCMeta'>",
|
| 101 |
":serialized:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
|
| 102 |
"__module__": "stable_baselines3.common.buffers",
|
| 103 |
+
"__doc__": "\n Replay buffer used in off-policy algorithms like SAC/TD3.\n\n :param buffer_size: Max number of element in the buffer\n :param observation_space: Observation space\n :param action_space: Action space\n :param device: PyTorch device\n :param n_envs: Number of parallel environments\n :param optimize_memory_usage: Enable a memory efficient variant\n of the replay buffer which reduces by almost a factor two the memory used,\n at a cost of more complexity.\n See https://github.com/DLR-RM/stable-baselines3/issues/37#issuecomment-637501195\n and https://github.com/DLR-RM/stable-baselines3/pull/28#issuecomment-637559274\n Cannot be used in combination with handle_timeout_termination.\n :param handle_timeout_termination: Handle timeout termination (due to timelimit)\n separately and treat the task as infinite horizon task.\n https://github.com/DLR-RM/stable-baselines3/issues/284\n ",
|
| 104 |
+
"__init__": "<function ReplayBuffer.__init__ at 0x7f094c0230d0>",
|
| 105 |
+
"add": "<function ReplayBuffer.add at 0x7f094c023160>",
|
| 106 |
+
"sample": "<function ReplayBuffer.sample at 0x7f094c0231f0>",
|
| 107 |
+
"_get_samples": "<function ReplayBuffer._get_samples at 0x7f094c023280>",
|
| 108 |
"__abstractmethods__": "frozenset()",
|
| 109 |
+
"_abc_impl": "<_abc_data object at 0x7f094c0a3300>"
|
| 110 |
},
|
| 111 |
"replay_buffer_kwargs": {},
|
| 112 |
"train_freq": {
|
|
|
|
| 116 |
"use_sde_at_warmup": false,
|
| 117 |
"target_entropy": -17.0,
|
| 118 |
"ent_coef": "auto",
|
| 119 |
+
"target_update_interval": 1,
|
| 120 |
+
"batch_norm_stats": [],
|
| 121 |
+
"batch_norm_stats_target": []
|
| 122 |
}
|
sac-seals-Humanoid-v0/ent_coef_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 sha256:402ccdfcedda955dd4f581529cb8ce5a6f792b741313ec469b29b6a091460209
|
| 3 |
+
size 1507
|
sac-seals-Humanoid-v0/policy.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5602821
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e1c552c40a88360fa4aa39d2b394e3cf0b8be94040591017234a6aee37e519d0
|
| 3 |
size 5602821
|
sac-seals-Humanoid-v0/pytorch_variables.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 747
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b3343fe033de69e1ec9093cc20d2ab342245f338e6ecb8797f825e01c50ec108
|
| 3 |
size 747
|
sac-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
|
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:fc5cb49b33425d16a561d10d48d454fdf20d266df98e1e06930fecb063872ffc
|
| 3 |
+
size 66544
|