Initial commit
Browse files- .gitattributes +1 -0
- README.md +84 -0
- args.yml +81 -0
- config.yml +25 -0
- env_kwargs.yml +1 -0
- replay.mp4 +3 -0
- results.json +1 -0
- sac-seals-HalfCheetah-v1.zip +3 -0
- sac-seals-HalfCheetah-v1/_stable_baselines3_version +1 -0
- sac-seals-HalfCheetah-v1/actor.optimizer.pth +3 -0
- sac-seals-HalfCheetah-v1/critic.optimizer.pth +3 -0
- sac-seals-HalfCheetah-v1/data +129 -0
- sac-seals-HalfCheetah-v1/ent_coef_optimizer.pth +3 -0
- sac-seals-HalfCheetah-v1/policy.pth +3 -0
- sac-seals-HalfCheetah-v1/pytorch_variables.pth +3 -0
- sac-seals-HalfCheetah-v1/system_info.txt +9 -0
- train_eval_metrics.zip +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
*.mp4 filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: stable-baselines3
|
3 |
+
tags:
|
4 |
+
- seals/HalfCheetah-v1
|
5 |
+
- deep-reinforcement-learning
|
6 |
+
- reinforcement-learning
|
7 |
+
- stable-baselines3
|
8 |
+
model-index:
|
9 |
+
- name: SAC
|
10 |
+
results:
|
11 |
+
- task:
|
12 |
+
type: reinforcement-learning
|
13 |
+
name: reinforcement-learning
|
14 |
+
dataset:
|
15 |
+
name: seals/HalfCheetah-v1
|
16 |
+
type: seals/HalfCheetah-v1
|
17 |
+
metrics:
|
18 |
+
- type: mean_reward
|
19 |
+
value: 1183.52 +/- 22.65
|
20 |
+
name: mean_reward
|
21 |
+
verified: false
|
22 |
+
---
|
23 |
+
|
24 |
+
# **SAC** Agent playing **seals/HalfCheetah-v1**
|
25 |
+
This is a trained model of a **SAC** agent playing **seals/HalfCheetah-v1**
|
26 |
+
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
|
27 |
+
and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
|
28 |
+
|
29 |
+
The RL Zoo is a training framework for Stable Baselines3
|
30 |
+
reinforcement learning agents,
|
31 |
+
with hyperparameter optimization and pre-trained agents included.
|
32 |
+
|
33 |
+
## Usage (with SB3 RL Zoo)
|
34 |
+
|
35 |
+
RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
|
36 |
+
SB3: https://github.com/DLR-RM/stable-baselines3<br/>
|
37 |
+
SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
|
38 |
+
|
39 |
+
Install the RL Zoo (with SB3 and SB3-Contrib):
|
40 |
+
```bash
|
41 |
+
pip install rl_zoo3
|
42 |
+
```
|
43 |
+
|
44 |
+
```
|
45 |
+
# Download model and save it into the logs/ folder
|
46 |
+
python -m rl_zoo3.load_from_hub --algo sac --env seals/HalfCheetah-v1 -orga HumanCompatibleAI -f logs/
|
47 |
+
python -m rl_zoo3.enjoy --algo sac --env seals/HalfCheetah-v1 -f logs/
|
48 |
+
```
|
49 |
+
|
50 |
+
If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
|
51 |
+
```
|
52 |
+
python -m rl_zoo3.load_from_hub --algo sac --env seals/HalfCheetah-v1 -orga HumanCompatibleAI -f logs/
|
53 |
+
python -m rl_zoo3.enjoy --algo sac --env seals/HalfCheetah-v1 -f logs/
|
54 |
+
```
|
55 |
+
|
56 |
+
## Training (with the RL Zoo)
|
57 |
+
```
|
58 |
+
python -m rl_zoo3.train --algo sac --env seals/HalfCheetah-v1 -f logs/
|
59 |
+
# Upload the model and generate video (when possible)
|
60 |
+
python -m rl_zoo3.push_to_hub --algo sac --env seals/HalfCheetah-v1 -f logs/ -orga HumanCompatibleAI
|
61 |
+
```
|
62 |
+
|
63 |
+
## Hyperparameters
|
64 |
+
```python
|
65 |
+
OrderedDict([('batch_size', 2048),
|
66 |
+
('buffer_size', 100000),
|
67 |
+
('gamma', 0.95),
|
68 |
+
('learning_rate', 0.000884624878315995),
|
69 |
+
('learning_starts', 10000),
|
70 |
+
('n_timesteps', 1000000.0),
|
71 |
+
('policy', 'MlpPolicy'),
|
72 |
+
('policy_kwargs',
|
73 |
+
{'log_std_init': -0.6932709443503001,
|
74 |
+
'net_arch': [64, 64],
|
75 |
+
'use_sde': False}),
|
76 |
+
('tau', 0.01),
|
77 |
+
('train_freq', 64),
|
78 |
+
('normalize', False)])
|
79 |
+
```
|
80 |
+
|
81 |
+
# Environment Arguments
|
82 |
+
```python
|
83 |
+
{'render_mode': 'rgb_array'}
|
84 |
+
```
|
args.yml
ADDED
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
!!python/object/apply:collections.OrderedDict
|
2 |
+
- - - algo
|
3 |
+
- sac
|
4 |
+
- - conf_file
|
5 |
+
- hyperparams/python/sac.py
|
6 |
+
- - device
|
7 |
+
- cpu
|
8 |
+
- - env
|
9 |
+
- seals/HalfCheetah-v1
|
10 |
+
- - env_kwargs
|
11 |
+
- null
|
12 |
+
- - eval_episodes
|
13 |
+
- 0
|
14 |
+
- - eval_freq
|
15 |
+
- 25000
|
16 |
+
- - gym_packages
|
17 |
+
- - seals
|
18 |
+
- - hyperparams
|
19 |
+
- null
|
20 |
+
- - log_folder
|
21 |
+
- gymnasium_models
|
22 |
+
- - log_interval
|
23 |
+
- -1
|
24 |
+
- - max_total_trials
|
25 |
+
- null
|
26 |
+
- - n_eval_envs
|
27 |
+
- 1
|
28 |
+
- - n_evaluations
|
29 |
+
- null
|
30 |
+
- - n_jobs
|
31 |
+
- 1
|
32 |
+
- - n_startup_trials
|
33 |
+
- 10
|
34 |
+
- - n_timesteps
|
35 |
+
- -1
|
36 |
+
- - n_trials
|
37 |
+
- 500
|
38 |
+
- - no_optim_plots
|
39 |
+
- false
|
40 |
+
- - num_threads
|
41 |
+
- 4
|
42 |
+
- - optimization_log_path
|
43 |
+
- null
|
44 |
+
- - optimize_hyperparameters
|
45 |
+
- false
|
46 |
+
- - progress
|
47 |
+
- false
|
48 |
+
- - pruner
|
49 |
+
- median
|
50 |
+
- - sampler
|
51 |
+
- tpe
|
52 |
+
- - save_freq
|
53 |
+
- -1
|
54 |
+
- - save_replay_buffer
|
55 |
+
- false
|
56 |
+
- - seed
|
57 |
+
- 2958364144
|
58 |
+
- - storage
|
59 |
+
- null
|
60 |
+
- - study_name
|
61 |
+
- null
|
62 |
+
- - tensorboard_log
|
63 |
+
- ''
|
64 |
+
- - track
|
65 |
+
- false
|
66 |
+
- - trained_agent
|
67 |
+
- ''
|
68 |
+
- - truncate_last_trajectory
|
69 |
+
- true
|
70 |
+
- - uuid
|
71 |
+
- false
|
72 |
+
- - vec_env
|
73 |
+
- dummy
|
74 |
+
- - verbose
|
75 |
+
- 1
|
76 |
+
- - wandb_entity
|
77 |
+
- null
|
78 |
+
- - wandb_project_name
|
79 |
+
- sb3
|
80 |
+
- - wandb_tags
|
81 |
+
- []
|
config.yml
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
!!python/object/apply:collections.OrderedDict
|
2 |
+
- - - batch_size
|
3 |
+
- 2048
|
4 |
+
- - buffer_size
|
5 |
+
- 100000
|
6 |
+
- - gamma
|
7 |
+
- 0.95
|
8 |
+
- - learning_rate
|
9 |
+
- 0.000884624878315995
|
10 |
+
- - learning_starts
|
11 |
+
- 10000
|
12 |
+
- - n_timesteps
|
13 |
+
- 1000000.0
|
14 |
+
- - policy
|
15 |
+
- MlpPolicy
|
16 |
+
- - policy_kwargs
|
17 |
+
- log_std_init: -0.6932709443503001
|
18 |
+
net_arch:
|
19 |
+
- 64
|
20 |
+
- 64
|
21 |
+
use_sde: false
|
22 |
+
- - tau
|
23 |
+
- 0.01
|
24 |
+
- - train_freq
|
25 |
+
- 64
|
env_kwargs.yml
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
render_mode: rgb_array
|
replay.mp4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:03d977c437d6d6482691926d4170d09b1b96c6f5321d06e5a29e7170de8411f3
|
3 |
+
size 2427924
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 1183.5162696, "std_reward": 22.649349480775626, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-19T11:52:51.514375"}
|
sac-seals-HalfCheetah-v1.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4532b2991f27daee4738c580c0e9a8ea69453b144fdeb7b3351c0865fac93dd4
|
3 |
+
size 305704
|
sac-seals-HalfCheetah-v1/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
2.2.0a3
|
sac-seals-HalfCheetah-v1/actor.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3098a35c186fec615721ef063e017aa78acdfd2c70e1c3846140100aa2351e90
|
3 |
+
size 55453
|
sac-seals-HalfCheetah-v1/critic.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:789843bffdbb6f5d2170d344cb3ad732d4f9921699b06bdbfb0a684d9d07fae6
|
3 |
+
size 102329
|
sac-seals-HalfCheetah-v1/data
ADDED
@@ -0,0 +1,129 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"policy_class": {
|
3 |
+
":type:": "<class 'abc.ABCMeta'>",
|
4 |
+
":serialized:": "gAWVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLnNhYy5wb2xpY2llc5SMCVNBQ1BvbGljeZSTlC4=",
|
5 |
+
"__module__": "stable_baselines3.sac.policies",
|
6 |
+
"__annotations__": "{'actor': <class 'stable_baselines3.sac.policies.Actor'>, 'critic': <class 'stable_baselines3.common.policies.ContinuousCritic'>, 'critic_target': <class 'stable_baselines3.common.policies.ContinuousCritic'>}",
|
7 |
+
"__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 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 ",
|
8 |
+
"__init__": "<function SACPolicy.__init__ at 0x7ff313e89700>",
|
9 |
+
"_build": "<function SACPolicy._build at 0x7ff313e89790>",
|
10 |
+
"_get_constructor_parameters": "<function SACPolicy._get_constructor_parameters at 0x7ff313e89820>",
|
11 |
+
"reset_noise": "<function SACPolicy.reset_noise at 0x7ff313e898b0>",
|
12 |
+
"make_actor": "<function SACPolicy.make_actor at 0x7ff313e89940>",
|
13 |
+
"make_critic": "<function SACPolicy.make_critic at 0x7ff313e899d0>",
|
14 |
+
"forward": "<function SACPolicy.forward at 0x7ff313e89a60>",
|
15 |
+
"_predict": "<function SACPolicy._predict at 0x7ff313e89af0>",
|
16 |
+
"set_training_mode": "<function SACPolicy.set_training_mode at 0x7ff313e89b80>",
|
17 |
+
"__abstractmethods__": "frozenset()",
|
18 |
+
"_abc_impl": "<_abc_data object at 0x7ff313e80b40>"
|
19 |
+
},
|
20 |
+
"verbose": 1,
|
21 |
+
"policy_kwargs": {
|
22 |
+
"net_arch": [
|
23 |
+
64,
|
24 |
+
64
|
25 |
+
],
|
26 |
+
"log_std_init": -0.6932709443503001,
|
27 |
+
"use_sde": false
|
28 |
+
},
|
29 |
+
"num_timesteps": 1000000,
|
30 |
+
"_total_timesteps": 1000000,
|
31 |
+
"_num_timesteps_at_start": 0,
|
32 |
+
"seed": 0,
|
33 |
+
"action_noise": null,
|
34 |
+
"start_time": 1694771152497198306,
|
35 |
+
"learning_rate": {
|
36 |
+
":type:": "<class 'function'>",
|
37 |
+
":serialized:": "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"
|
38 |
+
},
|
39 |
+
"tensorboard_log": null,
|
40 |
+
"_last_obs": null,
|
41 |
+
"_last_episode_starts": {
|
42 |
+
":type:": "<class 'numpy.ndarray'>",
|
43 |
+
":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
|
44 |
+
},
|
45 |
+
"_last_original_obs": {
|
46 |
+
":type:": "<class 'numpy.ndarray'>",
|
47 |
+
":serialized:": "gAWVBQEAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaQAAAAAAAAAArbnzHbxFJA7/V3QWPb3L9mOu9+IQMMQIon2RFVBeG/ySGl81MI5b8iH4g7bw/SP1ynJSlQw8I/5VlgdExc3T+UlV5h2GHRPwZyEkVM2PQ/8whm69pbyz9YLvYXASj0v2mr/OJJ7eE/+GLJfltS5b/e2lOclzQbwAlSG11CRB3AECktt6c4B0ApBR/0NTgTwJSMBW51bXB5lIwFZHR5cGWUk5SMAmY4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsShpSMAUOUdJRSlC4="
|
48 |
+
},
|
49 |
+
"_episode_num": 1000,
|
50 |
+
"use_sde": false,
|
51 |
+
"sde_sample_freq": -1,
|
52 |
+
"_current_progress_remaining": 0.0,
|
53 |
+
"_stats_window_size": 100,
|
54 |
+
"ep_info_buffer": {
|
55 |
+
":type:": "<class 'collections.deque'>",
|
56 |
+
":serialized:": "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"
|
57 |
+
},
|
58 |
+
"ep_success_buffer": {
|
59 |
+
":type:": "<class 'collections.deque'>",
|
60 |
+
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
61 |
+
},
|
62 |
+
"_n_updates": 15469,
|
63 |
+
"observation_space": {
|
64 |
+
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
65 |
+
":serialized:": "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",
|
66 |
+
"dtype": "float64",
|
67 |
+
"bounded_below": "[False False False False False False False False False False False False\n False False False False False False]",
|
68 |
+
"bounded_above": "[False False False False False False False False False False False False\n False False False False False False]",
|
69 |
+
"_shape": [
|
70 |
+
18
|
71 |
+
],
|
72 |
+
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf]",
|
73 |
+
"high": "[inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf]",
|
74 |
+
"low_repr": "-inf",
|
75 |
+
"high_repr": "inf",
|
76 |
+
"_np_random": null
|
77 |
+
},
|
78 |
+
"action_space": {
|
79 |
+
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
80 |
+
":serialized:": "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",
|
81 |
+
"dtype": "float32",
|
82 |
+
"bounded_below": "[ True True True True True True]",
|
83 |
+
"bounded_above": "[ True True True True True True]",
|
84 |
+
"_shape": [
|
85 |
+
6
|
86 |
+
],
|
87 |
+
"low": "[-1. -1. -1. -1. -1. -1.]",
|
88 |
+
"high": "[1. 1. 1. 1. 1. 1.]",
|
89 |
+
"low_repr": "-1.0",
|
90 |
+
"high_repr": "1.0",
|
91 |
+
"_np_random": "Generator(PCG64)"
|
92 |
+
},
|
93 |
+
"n_envs": 1,
|
94 |
+
"buffer_size": 1,
|
95 |
+
"batch_size": 2048,
|
96 |
+
"learning_starts": 10000,
|
97 |
+
"tau": 0.01,
|
98 |
+
"gamma": 0.95,
|
99 |
+
"gradient_steps": 1,
|
100 |
+
"optimize_memory_usage": false,
|
101 |
+
"replay_buffer_class": {
|
102 |
+
":type:": "<class 'abc.ABCMeta'>",
|
103 |
+
":serialized:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
|
104 |
+
"__module__": "stable_baselines3.common.buffers",
|
105 |
+
"__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 ",
|
106 |
+
"__init__": "<function ReplayBuffer.__init__ at 0x7ff313ed7700>",
|
107 |
+
"add": "<function ReplayBuffer.add at 0x7ff313ed7790>",
|
108 |
+
"sample": "<function ReplayBuffer.sample at 0x7ff313ed7820>",
|
109 |
+
"_get_samples": "<function ReplayBuffer._get_samples at 0x7ff313ed78b0>",
|
110 |
+
"_maybe_cast_dtype": "<staticmethod object at 0x7ff313ed0850>",
|
111 |
+
"__abstractmethods__": "frozenset()",
|
112 |
+
"_abc_impl": "<_abc_data object at 0x7ff313ed0870>"
|
113 |
+
},
|
114 |
+
"replay_buffer_kwargs": {},
|
115 |
+
"train_freq": {
|
116 |
+
":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
|
117 |
+
":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLQGgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
|
118 |
+
},
|
119 |
+
"use_sde_at_warmup": false,
|
120 |
+
"target_entropy": -6.0,
|
121 |
+
"ent_coef": "auto",
|
122 |
+
"target_update_interval": 1,
|
123 |
+
"lr_schedule": {
|
124 |
+
":type:": "<class 'function'>",
|
125 |
+
":serialized:": "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"
|
126 |
+
},
|
127 |
+
"batch_norm_stats": [],
|
128 |
+
"batch_norm_stats_target": []
|
129 |
+
}
|
sac-seals-HalfCheetah-v1/ent_coef_optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c7b6e2491976823ed5614ebbe99fc5bac520cd032e37f6fa8c689af1fa34a5df
|
3 |
+
size 1507
|
sac-seals-HalfCheetah-v1/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62d61ccfb530d7d0f7c5b041c05dbb97d2ad871d8949dfa6bb10aeb2ac5878dc
|
3 |
+
size 128261
|
sac-seals-HalfCheetah-v1/pytorch_variables.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:efbdbacbd3325e414982ffd4d836a76db7baf1abde4778bc1ff76ad0c66eb925
|
3 |
+
size 747
|
sac-seals-HalfCheetah-v1/system_info.txt
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
- OS: Linux-5.4.0-156-generic-x86_64-with-glibc2.29 # 173-Ubuntu SMP Tue Jul 11 07:25:22 UTC 2023
|
2 |
+
- Python: 3.8.10
|
3 |
+
- Stable-Baselines3: 2.2.0a3
|
4 |
+
- PyTorch: 2.0.1+cu117
|
5 |
+
- GPU Enabled: False
|
6 |
+
- Numpy: 1.24.4
|
7 |
+
- Cloudpickle: 2.2.1
|
8 |
+
- Gymnasium: 0.29.1
|
9 |
+
- OpenAI Gym: 0.21.0
|
train_eval_metrics.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:be506b28850193dd6638a80f4c095c21b27d667a226cd16e87193ec97bbf5238
|
3 |
+
size 29294
|