Commit
•
9a3bc92
1
Parent(s):
44197c1
Initial commit
Browse files- .gitattributes +1 -0
- README.md +85 -0
- args.yml +59 -0
- config.yml +29 -0
- env_kwargs.yml +1 -0
- replay.mp4 +3 -0
- results.json +1 -0
- tqc-Walker2DBulletEnv-v0.zip +3 -0
- tqc-Walker2DBulletEnv-v0/_stable_baselines3_version +1 -0
- tqc-Walker2DBulletEnv-v0/actor.optimizer.pth +3 -0
- tqc-Walker2DBulletEnv-v0/critic.optimizer.pth +3 -0
- tqc-Walker2DBulletEnv-v0/data +130 -0
- tqc-Walker2DBulletEnv-v0/ent_coef_optimizer.pth +3 -0
- tqc-Walker2DBulletEnv-v0/policy.pth +3 -0
- tqc-Walker2DBulletEnv-v0/pytorch_variables.pth +3 -0
- tqc-Walker2DBulletEnv-v0/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 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: stable-baselines3
|
3 |
+
tags:
|
4 |
+
- Walker2DBulletEnv-v0
|
5 |
+
- deep-reinforcement-learning
|
6 |
+
- reinforcement-learning
|
7 |
+
- stable-baselines3
|
8 |
+
model-index:
|
9 |
+
- name: TQC
|
10 |
+
results:
|
11 |
+
- task:
|
12 |
+
type: reinforcement-learning
|
13 |
+
name: reinforcement-learning
|
14 |
+
dataset:
|
15 |
+
name: Walker2DBulletEnv-v0
|
16 |
+
type: Walker2DBulletEnv-v0
|
17 |
+
metrics:
|
18 |
+
- type: mean_reward
|
19 |
+
value: 2674.29 +/- 5.47
|
20 |
+
name: mean_reward
|
21 |
+
verified: false
|
22 |
+
---
|
23 |
+
|
24 |
+
# **TQC** Agent playing **Walker2DBulletEnv-v0**
|
25 |
+
This is a trained model of a **TQC** agent playing **Walker2DBulletEnv-v0**
|
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 tqc --env Walker2DBulletEnv-v0 -orga Emperor-WS -f logs/
|
47 |
+
python -m rl_zoo3.enjoy --algo tqc --env Walker2DBulletEnv-v0 -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 tqc --env Walker2DBulletEnv-v0 -orga Emperor-WS -f logs/
|
53 |
+
python -m rl_zoo3.enjoy --algo tqc --env Walker2DBulletEnv-v0 -f logs/
|
54 |
+
```
|
55 |
+
|
56 |
+
## Training (with the RL Zoo)
|
57 |
+
```
|
58 |
+
python -m rl_zoo3.train --algo tqc --env Walker2DBulletEnv-v0 -f logs/
|
59 |
+
# Upload the model and generate video (when possible)
|
60 |
+
python -m rl_zoo3.push_to_hub --algo tqc --env Walker2DBulletEnv-v0 -f logs/ -orga Emperor-WS
|
61 |
+
```
|
62 |
+
|
63 |
+
## Hyperparameters
|
64 |
+
```python
|
65 |
+
OrderedDict([('batch_size', 256),
|
66 |
+
('buffer_size', 300000),
|
67 |
+
('ent_coef', 'auto'),
|
68 |
+
('env_wrapper', 'sb3_contrib.common.wrappers.TimeFeatureWrapper'),
|
69 |
+
('gamma', 0.98),
|
70 |
+
('gradient_steps', 64),
|
71 |
+
('learning_rate', 'lin_7.3e-4'),
|
72 |
+
('learning_starts', 10000),
|
73 |
+
('n_timesteps', 1000000.0),
|
74 |
+
('policy', 'MlpPolicy'),
|
75 |
+
('policy_kwargs', 'dict(log_std_init=-3, net_arch=[400, 300])'),
|
76 |
+
('tau', 0.02),
|
77 |
+
('train_freq', 64),
|
78 |
+
('use_sde', True),
|
79 |
+
('normalize', False)])
|
80 |
+
```
|
81 |
+
|
82 |
+
# Environment Arguments
|
83 |
+
```python
|
84 |
+
{'render_mode': 'rgb_array'}
|
85 |
+
```
|
args.yml
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
!!python/object/apply:collections.OrderedDict
|
2 |
+
- - - algo
|
3 |
+
- tqc
|
4 |
+
- - env
|
5 |
+
- Walker2DBulletEnv-v0
|
6 |
+
- - env_kwargs
|
7 |
+
- null
|
8 |
+
- - eval_episodes
|
9 |
+
- 10
|
10 |
+
- - eval_freq
|
11 |
+
- 10000
|
12 |
+
- - gym_packages
|
13 |
+
- []
|
14 |
+
- - hyperparams
|
15 |
+
- null
|
16 |
+
- - log_folder
|
17 |
+
- rl-trained-agents/
|
18 |
+
- - log_interval
|
19 |
+
- -1
|
20 |
+
- - n_evaluations
|
21 |
+
- 20
|
22 |
+
- - n_jobs
|
23 |
+
- 1
|
24 |
+
- - n_startup_trials
|
25 |
+
- 10
|
26 |
+
- - n_timesteps
|
27 |
+
- -1
|
28 |
+
- - n_trials
|
29 |
+
- 10
|
30 |
+
- - num_threads
|
31 |
+
- -1
|
32 |
+
- - optimize_hyperparameters
|
33 |
+
- false
|
34 |
+
- - pruner
|
35 |
+
- median
|
36 |
+
- - sampler
|
37 |
+
- tpe
|
38 |
+
- - save_freq
|
39 |
+
- -1
|
40 |
+
- - save_replay_buffer
|
41 |
+
- false
|
42 |
+
- - seed
|
43 |
+
- 1908048640
|
44 |
+
- - storage
|
45 |
+
- null
|
46 |
+
- - study_name
|
47 |
+
- null
|
48 |
+
- - tensorboard_log
|
49 |
+
- ''
|
50 |
+
- - trained_agent
|
51 |
+
- ''
|
52 |
+
- - truncate_last_trajectory
|
53 |
+
- true
|
54 |
+
- - uuid
|
55 |
+
- true
|
56 |
+
- - vec_env
|
57 |
+
- dummy
|
58 |
+
- - verbose
|
59 |
+
- 1
|
config.yml
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
!!python/object/apply:collections.OrderedDict
|
2 |
+
- - - batch_size
|
3 |
+
- 256
|
4 |
+
- - buffer_size
|
5 |
+
- 300000
|
6 |
+
- - ent_coef
|
7 |
+
- auto
|
8 |
+
- - env_wrapper
|
9 |
+
- sb3_contrib.common.wrappers.TimeFeatureWrapper
|
10 |
+
- - gamma
|
11 |
+
- 0.98
|
12 |
+
- - gradient_steps
|
13 |
+
- 64
|
14 |
+
- - learning_rate
|
15 |
+
- lin_7.3e-4
|
16 |
+
- - learning_starts
|
17 |
+
- 10000
|
18 |
+
- - n_timesteps
|
19 |
+
- 1000000.0
|
20 |
+
- - policy
|
21 |
+
- MlpPolicy
|
22 |
+
- - policy_kwargs
|
23 |
+
- dict(log_std_init=-3, net_arch=[400, 300])
|
24 |
+
- - tau
|
25 |
+
- 0.02
|
26 |
+
- - train_freq
|
27 |
+
- 64
|
28 |
+
- - use_sde
|
29 |
+
- true
|
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:ac03f121883d65cfac4a693a072b4241a43136f85ac123acc7b45b8499b68888
|
3 |
+
size 1122852
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 2674.2946613, "std_reward": 5.469212969134861, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-02-29T21:55:54.520702"}
|
tqc-Walker2DBulletEnv-v0.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:00bd3a6b586cf711ceb75d66ce0bbd4c6d9f059439dcbc1fbf2e342236275a9e
|
3 |
+
size 6122053
|
tqc-Walker2DBulletEnv-v0/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
2.3.0a2
|
tqc-Walker2DBulletEnv-v0/actor.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:399a531238f8afc8a9f6542210d28a6a670981907fae11af1495764b2787e5e0
|
3 |
+
size 1073879
|
tqc-Walker2DBulletEnv-v0/critic.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bcffaf85701bc2bbf18400e06514b709e422664102f17381e6c2d0599661c0f5
|
3 |
+
size 2246378
|
tqc-Walker2DBulletEnv-v0/data
ADDED
@@ -0,0 +1,130 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"policy_class": {
|
3 |
+
":type:": "<class 'abc.ABCMeta'>",
|
4 |
+
":serialized:": "gAWVKgAAAAAAAACMGHNiM19jb250cmliLnRxYy5wb2xpY2llc5SMCVRRQ1BvbGljeZSTlC4=",
|
5 |
+
"__module__": "sb3_contrib.tqc.policies",
|
6 |
+
"__annotations__": "{'actor': <class 'sb3_contrib.tqc.policies.Actor'>, 'critic': <class 'sb3_contrib.tqc.policies.Critic'>, 'critic_target': <class 'sb3_contrib.tqc.policies.Critic'>}",
|
7 |
+
"__doc__": "\n Policy class (with both actor and critic) for TQC.\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 feature 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_quantiles: Number of quantiles for the critic.\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 TQCPolicy.__init__ at 0x7d5526f8f370>",
|
9 |
+
"_build": "<function TQCPolicy._build at 0x7d5526f8f400>",
|
10 |
+
"_get_constructor_parameters": "<function TQCPolicy._get_constructor_parameters at 0x7d5526f8f490>",
|
11 |
+
"reset_noise": "<function TQCPolicy.reset_noise at 0x7d5526f8f520>",
|
12 |
+
"make_actor": "<function TQCPolicy.make_actor at 0x7d5526f8f5b0>",
|
13 |
+
"make_critic": "<function TQCPolicy.make_critic at 0x7d5526f8f640>",
|
14 |
+
"forward": "<function TQCPolicy.forward at 0x7d5526f8f6d0>",
|
15 |
+
"_predict": "<function TQCPolicy._predict at 0x7d5526f8f760>",
|
16 |
+
"set_training_mode": "<function TQCPolicy.set_training_mode at 0x7d5526f8f7f0>",
|
17 |
+
"__abstractmethods__": "frozenset()",
|
18 |
+
"_abc_impl": "<_abc._abc_data object at 0x7d5526f79c00>"
|
19 |
+
},
|
20 |
+
"verbose": 1,
|
21 |
+
"policy_kwargs": {
|
22 |
+
"log_std_init": -3,
|
23 |
+
"net_arch": [
|
24 |
+
400,
|
25 |
+
300
|
26 |
+
],
|
27 |
+
"use_sde": true
|
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": 1614621441.9669518,
|
35 |
+
"learning_rate": 0.0003,
|
36 |
+
"tensorboard_log": null,
|
37 |
+
"_last_obs": null,
|
38 |
+
"_last_episode_starts": null,
|
39 |
+
"_last_original_obs": {
|
40 |
+
":type:": "<class 'numpy.ndarray'>",
|
41 |
+
":serialized:": "gAWV0QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZcAAAAAAAAANFCmL4AAAAAAACAP443RD8AAAAAQpN8vAAAAABI6na/QwKAP6+uD7rqrxu9T5I4P9pCHT9pdLs+JkAwPfglrjurCqg+0/EEvixfxj6xav++AAAAAAAAgD83iQE/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSxeGlIwBQ5R0lFKULg=="
|
42 |
+
},
|
43 |
+
"_episode_num": 2892,
|
44 |
+
"use_sde": true,
|
45 |
+
"sde_sample_freq": -1,
|
46 |
+
"_current_progress_remaining": 0.0,
|
47 |
+
"_stats_window_size": 100,
|
48 |
+
"ep_info_buffer": {
|
49 |
+
":type:": "<class 'collections.deque'>",
|
50 |
+
":serialized:": "gAWVJQwAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQIPuk5CF9KGMAWyUTQoBjAF0lEdA0a4enQpnYnV9lChoBkdAgR2NL127nWgHS/JoCEdA0a9BK0UoKHV9lChoBkdApCqNX7tRemgHTegDaAhHQNGzhtBF/hF1fZQoaAZHQHQh9fLLZBdoB0uQaAhHQNG0XClnAZd1fZQoaAZHQKQO1OXVsk9oB03oA2gIR0DRvSz4GlhxdX2UKGgGR0CkXYygPEsKaAdN6ANoCEdA0cGzgBLf13V9lChoBkdAd0+Ue+23KGgHS6doCEdA0cKKra/RFHV9lChoBkdAiOiX9aUzK2gHTUMBaAhHQNHD+vuLJjl1fZQoaAZHQFRNwTM7lq9oB0swaAhHQNHEARVyWAx1fZQoaAZHQKQ0P6SDAahoB03oA2gIR0DRyJWU3XI2dX2UKGgGR0CJCt77bcoIaAdNQwFoCEdA0coGVT72tnV9lChoBkdAnAqMVYZEUmgHTb4CaAhHQNHNJqSgXdl1fZQoaAZHQKKDEuh9LHxoB02YA2gIR0DR0RqMLncMdX2UKGgGR0CMq/0VafSQaAdNegFoCEdA0dLD60pmVnV9lChoBkdAhbt6YE4ecWgHTSABaAhHQNHUJnscABF1fZQoaAZHQKQRTupCKJloB03oA2gIR0DR2GmH58BudX2UKGgGR0CkH6NcfNiZaAdN6ANoCEdA0dztRmK64HV9lChoBkdApDUn1zySWGgHTegDaAhHQNHhcd03fhx1fZQoaAZHQKQ/kA6Mir1oB03oA2gIR0DR5bHFS88LdX2UKGgGR0CchOHZK3/haAdNwgJoCEdA0e0wc1fmcXV9lChoBkdApC2idhAnlWgHTegDaAhHQNHxxnUDuBt1fZQoaAZHQKQgEW+GoJloB03oA2gIR0DR9lDTTfBOdX2UKGgGR0CCVYjwhGH6aAdL9mgIR0DR9zO+pOvddX2UKGgGR0BgUJeb/ffoaAdLSGgIR0DR97xoSL62dX2UKGgGR0CKnENrj5sTaAdNUwFoCEdA0fktgUUO/nV9lChoBkdApEFBrJr+HmgHTegDaAhHQNH9fTCP6sR1fZQoaAZHQH3VfwAlv61oB0vOaAhHQNH+l0O3DvV1fZQoaAZHQJ4eXrX18LNoB03xAmgIR0DSAbRC+lCUdX2UKGgGR0CkS7VbiZOSaAdN6ANoCEdA0gY7U0Nz83V9lChoBkdATRwdXDFZPmgHSyNoCEdA0gaBb5/LDHV9lChoBkdAZKkjgQ6IWWgHS1VoCEdA0gbNTURWcXV9lChoBkdApE4zw4KhMGgHTegDaAhHQNILXqpPykN1fZQoaAZHQKRuH94NZvFoB03oA2gIR0DSD6bLxI8RdX2UKGgGR0BDlRYq5LAYaAdLHWgIR0DSD+xFLFn7dX2UKGgGR0CkfFo0ZWJaaAdN6ANoCEdA0hQqfR/mT3V9lChoBkdApClrnPmgamgHTegDaAhHQNIYs7eMyad1fZQoaAZHQIV9dea8YhtoB00dAWgIR0DSHnmTTvy9dX2UKGgGR0CCUzew9q1xaAdNAwFoCEdA0h+e88s+V3V9lChoBkdAUW+QLeANG2gHSypoCEdA0h/mA7xNI3V9lChoBkdApGbMkyDZlGgHTegDaAhHQNIkYbwWnCR1fZQoaAZHQICVbWPLgXNoB0vaaAhHQNIlOHIQvpR1fZQoaAZHQKQ7ECnxaxJoB03oA2gIR0DSKcQ6V+qjdX2UKGgGR0Cb6cujh1klaAdNtAJoCEdA0izgea8Yh3V9lChoBkdAYhenndO6/mgHS0poCEdA0i0pOmBOHnV9lChoBkdAN8OVLSNOumgHSxBoCEdA0i0rSh8IA3V9lChoBkdAmyctLpRoAWgHTaMCaAhHQNIv+CUxEfF1fZQoaAZHQHGXvoNd7fJoB0uIaAhHQNIwxrux8lZ1fZQoaAZHQH6yLA+IM0BoB0vPaAhHQNIxpI4p+c91fZQoaAZHQGdiDkuHvc9oB0tdaAhHQNIx8Y4EOiF1fZQoaAZHQKRILbDdgv1oB03oA2gIR0DSNmO8DjiodX2UKGgGR0CVdVwsoUi7aAdNGQJoCEdA0ji1nlnyu3V9lChoBkdApEey/fwZwWgHTegDaAhHQNI9PjhDPWx1fZQoaAZHQH86z15B1LdoB0vWaAhHQNI+EgB91EF1fZQoaAZHQHG2HCsOoYNoB0uCaAhHQNI+pEGzKLd1fZQoaAZHQKR51sgMc6xoB03oA2gIR0DSQzRoSL62dX2UKGgGR0Cj8zKMWGh3aAdN6ANoCEdA0kfLTrVvuXV9lChoBkdApGVIG0NSZWgHTegDaAhHQNJQ7tmxt551fZQoaAZHQKQFnubZvk1oB03oA2gIR0DSVZJ6+nIidX2UKGgGR0CkG2/dZaFFaAdN6ANoCEdA0lnxGXokiXV9lChoBkdAenZz7di2D2gHS7doCEdA0lrMOO8013V9lChoBkdApERixFAmiWgHTegDaAhHQNJfa5wbVBl1fZQoaAZHQKR42NMoMKFoB03oA2gIR0DSY/AH7gsLdX2UKGgGR0CkHYZssQNDaAdN6ANoCEdA0mhRt9QXRHV9lChoBkdApE9kNvwVkGgHTegDaAhHQNJs6wVoHs11fZQoaAZHQKRHEjXWe6JoB03oA2gIR0DScUPw3HaOdX2UKGgGR0CQ7xwvxpcpaAdNtwFoCEdA0nNJQwblzXV9lChoBkdAdB26HTI/7mgHS41oCEdA0nPSHOKO1nV9lChoBkdAfnWIcinpCGgHS9RoCEdA0nT6Dej2z3V9lChoBkdApDMMr9VFQWgHTegDaAhHQNJ5UkNnXd11fZQoaAZHQHOyLxNIsiBoB0uLaAhHQNJ6KJn+Q2d1fZQoaAZHQJxCRKf4AS5oB03JAmgIR0DSgh4Q5FPSdX2UKGgGR0A4IxoqTbFkaAdLEWgIR0DSgiBGPPszdX2UKGgGR0BjlgLRa5f/aAdLUGgIR0DSgm0HQhOhdX2UKGgGR0CkSk5bILgGaAdN6ANoCEdA0obzJ6IFeXV9lChoBkdApEouBSUC72gHTegDaAhHQNKLQtBWxQl1fZQoaAZHQKQuAnLJSzhoB03oA2gIR0DSj/nRiPQwdX2UKGgGR0BdGnvQWvbHaAdLPmgIR0DSkDuFuejEdX2UKGgGR0CkA9EC3gDSaAdN6ANoCEdA0pTWG6f8M3V9lChoBkdAZDyV4X40uWgHS1JoCEdA0pUhomXw9nV9lChoBkdAh5sLx7RfGGgHTToBaAhHQNKWg9oexOd1fZQoaAZHQKRhKYFaB7NoB03oA2gIR0DSmvs2606YdX2UKGgGR0CkIvG3WnTBaAdN6ANoCEdA0p82jzqbB3V9lChoBkdApEFu4NI9T2gHTegDaAhHQNKjvJswco91fZQoaAZHQKQ8TLq2SdRoB03oA2gIR0DSp/oMSbpedX2UKGgGR0CkNvi9Zid8aAdN6ANoCEdA0qyKiO/+KnV9lChoBkdApH22u/1xsGgHTegDaAhHQNK1qQgow251fZQoaAZHQKQ0bxHXmNloB03oA2gIR0DSufaYTj//dX2UKGgGR0CkWaZ7ojfOaAdN6ANoCEdA0r6mB7u2JHV9lChoBkdApDwsWO6un2gHTegDaAhHQNLDNvLLZBd1fZQoaAZHQKQlnwEyLydoB03oA2gIR0DSx4EDSw4bdX2UKGgGR0B1tnHXEqDsaAdLnGgIR0DSyFqsA/9pdX2UKGgGR0CHtxFkxyn2aAdNNAFoCEdA0smI57w8XHV9lChoBkdApENIGdI5HWgHTegDaAhHQNLN8krGza91fZQoaAZHQGV+1II4VARoB0tXaAhHQNLOP7BCUot1fZQoaAZHQIzH7kZJkG1oB01sAWgIR0DSz+5uyeI3dX2UKGgGR0B9Za7K7qY7aAdLymgIR0DS0MkPatcOdX2UKGgGR0BxvJsj3VTaaAdLiGgIR0DS0U7FaSs9dX2UKGgGR0CjxRUoa1kUaAdN6ANoCEdA0tXhqG1x83V9lChoBkdApEpS3ocJdGgHTegDaAhHQNLacLDZUUB1fZQoaAZHQIoJadhAnlZoB01LAWgIR0DS2+CzollcdWUu"
|
51 |
+
},
|
52 |
+
"ep_success_buffer": {
|
53 |
+
":type:": "<class 'collections.deque'>",
|
54 |
+
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
55 |
+
},
|
56 |
+
"_n_updates": 990016,
|
57 |
+
"observation_space": {
|
58 |
+
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
59 |
+
":serialized:": "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",
|
60 |
+
"dtype": "float32",
|
61 |
+
"bounded_below": "[False False False False False False False False False False False False\n False False False False False False False False False False True]",
|
62 |
+
"bounded_above": "[False False False False False False False False False False False False\n False False False False False False False False False False True]",
|
63 |
+
"_shape": [
|
64 |
+
23
|
65 |
+
],
|
66 |
+
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf 0.]",
|
67 |
+
"high": "[inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf 1.]",
|
68 |
+
"low_repr": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf 0.]",
|
69 |
+
"high_repr": "[inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf 1.]",
|
70 |
+
"_np_random": null
|
71 |
+
},
|
72 |
+
"action_space": {
|
73 |
+
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
74 |
+
":serialized:": "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",
|
75 |
+
"dtype": "float32",
|
76 |
+
"bounded_below": "[ True True True True True True]",
|
77 |
+
"bounded_above": "[ True True True True True True]",
|
78 |
+
"_shape": [
|
79 |
+
6
|
80 |
+
],
|
81 |
+
"low": "[-1. -1. -1. -1. -1. -1.]",
|
82 |
+
"high": "[1. 1. 1. 1. 1. 1.]",
|
83 |
+
"low_repr": "-1.0",
|
84 |
+
"high_repr": "1.0",
|
85 |
+
"_np_random": "Generator(PCG64)"
|
86 |
+
},
|
87 |
+
"n_envs": 1,
|
88 |
+
"buffer_size": 1,
|
89 |
+
"batch_size": 256,
|
90 |
+
"learning_starts": 10000,
|
91 |
+
"tau": 0.02,
|
92 |
+
"gamma": 0.98,
|
93 |
+
"gradient_steps": 64,
|
94 |
+
"optimize_memory_usage": false,
|
95 |
+
"replay_buffer_class": {
|
96 |
+
":type:": "<class 'abc.ABCMeta'>",
|
97 |
+
":serialized:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
|
98 |
+
"__module__": "stable_baselines3.common.buffers",
|
99 |
+
"__annotations__": "{'observations': <class 'numpy.ndarray'>, 'next_observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'dones': <class 'numpy.ndarray'>, 'timeouts': <class 'numpy.ndarray'>}",
|
100 |
+
"__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 ",
|
101 |
+
"__init__": "<function ReplayBuffer.__init__ at 0x7d552821a440>",
|
102 |
+
"add": "<function ReplayBuffer.add at 0x7d552821a4d0>",
|
103 |
+
"sample": "<function ReplayBuffer.sample at 0x7d552821a560>",
|
104 |
+
"_get_samples": "<function ReplayBuffer._get_samples at 0x7d552821a5f0>",
|
105 |
+
"_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x7d552821a680>)>",
|
106 |
+
"__abstractmethods__": "frozenset()",
|
107 |
+
"_abc_impl": "<_abc._abc_data object at 0x7d5528195600>"
|
108 |
+
},
|
109 |
+
"replay_buffer_kwargs": {},
|
110 |
+
"train_freq": {
|
111 |
+
":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
|
112 |
+
":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLQGgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
|
113 |
+
},
|
114 |
+
"use_sde_at_warmup": false,
|
115 |
+
"target_entropy": -6.0,
|
116 |
+
"ent_coef": "auto",
|
117 |
+
"target_update_interval": 1,
|
118 |
+
"top_quantiles_to_drop_per_net": 2,
|
119 |
+
"_last_dones": {
|
120 |
+
":type:": "<class 'numpy.ndarray'>",
|
121 |
+
":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
|
122 |
+
},
|
123 |
+
"remove_time_limit_termination": false,
|
124 |
+
"lr_schedule": {
|
125 |
+
":type:": "<class 'function'>",
|
126 |
+
":serialized:": "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"
|
127 |
+
},
|
128 |
+
"batch_norm_stats": [],
|
129 |
+
"batch_norm_stats_target": []
|
130 |
+
}
|
tqc-Walker2DBulletEnv-v0/ent_coef_optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eff5d4192fc6c9b4e2c10d2bccca0a83d16838cf1e9ae8f737d5acc566c604a0
|
3 |
+
size 1940
|
tqc-Walker2DBulletEnv-v0/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d9d44cf1f919de26a088b2104b70c04b3333c395d53565e634bc52e38e36f7a2
|
3 |
+
size 2781433
|
tqc-Walker2DBulletEnv-v0/pytorch_variables.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d161de64452f3a3d852fbe17a6764089638e52ececa8e22500b64f873b4b13b
|
3 |
+
size 1180
|
tqc-Walker2DBulletEnv-v0/system_info.txt
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
- OS: Linux-5.15.133+-x86_64-with-glibc2.31 # 1 SMP Tue Dec 19 13:14:11 UTC 2023
|
2 |
+
- Python: 3.10.13
|
3 |
+
- Stable-Baselines3: 2.3.0a2
|
4 |
+
- PyTorch: 2.1.2+cpu
|
5 |
+
- GPU Enabled: False
|
6 |
+
- Numpy: 1.26.3
|
7 |
+
- Cloudpickle: 2.2.1
|
8 |
+
- Gymnasium: 0.29.0
|
9 |
+
- OpenAI Gym: 0.26.2
|
train_eval_metrics.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c963d3e7ace1cb88910dc419d4cd61c37a396d3c64ec8f45d809c672723308a6
|
3 |
+
size 95481
|