Commit
•
bca2e39
1
Parent(s):
005e2db
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-AntBulletEnv-v0.zip +3 -0
- tqc-AntBulletEnv-v0/_stable_baselines3_version +1 -0
- tqc-AntBulletEnv-v0/actor.optimizer.pth +3 -0
- tqc-AntBulletEnv-v0/critic.optimizer.pth +3 -0
- tqc-AntBulletEnv-v0/data +130 -0
- tqc-AntBulletEnv-v0/ent_coef_optimizer.pth +3 -0
- tqc-AntBulletEnv-v0/policy.pth +3 -0
- tqc-AntBulletEnv-v0/pytorch_variables.pth +3 -0
- tqc-AntBulletEnv-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 |
+
- AntBulletEnv-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: AntBulletEnv-v0
|
16 |
+
type: AntBulletEnv-v0
|
17 |
+
metrics:
|
18 |
+
- type: mean_reward
|
19 |
+
value: 3483.69 +/- 16.40
|
20 |
+
name: mean_reward
|
21 |
+
verified: false
|
22 |
+
---
|
23 |
+
|
24 |
+
# **TQC** Agent playing **AntBulletEnv-v0**
|
25 |
+
This is a trained model of a **TQC** agent playing **AntBulletEnv-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 AntBulletEnv-v0 -orga Emperor-WS -f logs/
|
47 |
+
python -m rl_zoo3.enjoy --algo tqc --env AntBulletEnv-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 AntBulletEnv-v0 -orga Emperor-WS -f logs/
|
53 |
+
python -m rl_zoo3.enjoy --algo tqc --env AntBulletEnv-v0 -f logs/
|
54 |
+
```
|
55 |
+
|
56 |
+
## Training (with the RL Zoo)
|
57 |
+
```
|
58 |
+
python -m rl_zoo3.train --algo tqc --env AntBulletEnv-v0 -f logs/
|
59 |
+
# Upload the model and generate video (when possible)
|
60 |
+
python -m rl_zoo3.push_to_hub --algo tqc --env AntBulletEnv-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', 0.00073),
|
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 |
+
- AntBulletEnv-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 |
+
- 2054332755
|
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 |
+
- 0.00073
|
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:ccd60c5001eb8eaabd286cefa463f2b391333efa28cb5d8229cfc6c147cdc6e3
|
3 |
+
size 1286334
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 3483.6901841999997, "std_reward": 16.395939155759937, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-01T01:23:53.982935"}
|
tqc-AntBulletEnv-v0.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d73086b951ec6368e8a66600b8accccca9530bbd022dc41037d10247546071a9
|
3 |
+
size 6268199
|
tqc-AntBulletEnv-v0/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
2.3.0a2
|
tqc-AntBulletEnv-v0/actor.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e26366b41e9226c348569f7fa32a23a8f72ec3e52ce5ee2d8618dc49062ec35c
|
3 |
+
size 1102807
|
tqc-AntBulletEnv-v0/critic.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cffbc7a334ef6336f9aa47f181384f02b6d0d22a822c09d1a698dde09de0b4ee
|
3 |
+
size 2297578
|
tqc-AntBulletEnv-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 0x7cdbcb477520>",
|
9 |
+
"_build": "<function TQCPolicy._build at 0x7cdbcb4775b0>",
|
10 |
+
"_get_constructor_parameters": "<function TQCPolicy._get_constructor_parameters at 0x7cdbcb477640>",
|
11 |
+
"reset_noise": "<function TQCPolicy.reset_noise at 0x7cdbcb4776d0>",
|
12 |
+
"make_actor": "<function TQCPolicy.make_actor at 0x7cdbcb477760>",
|
13 |
+
"make_critic": "<function TQCPolicy.make_critic at 0x7cdbcb4777f0>",
|
14 |
+
"forward": "<function TQCPolicy.forward at 0x7cdbcb477880>",
|
15 |
+
"_predict": "<function TQCPolicy._predict at 0x7cdbcb477910>",
|
16 |
+
"set_training_mode": "<function TQCPolicy.set_training_mode at 0x7cdbcb4779a0>",
|
17 |
+
"__abstractmethods__": "frozenset()",
|
18 |
+
"_abc_impl": "<_abc._abc_data object at 0x7cdbcb485f80>"
|
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": 1614621417.2337935,
|
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:": "gAWV6QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZ0AAAAAAAAAMfRO74Ffrm+2ptuPydWdz+REN29IfERvtcfX7013YS+H7jHPi30ar+jX4I+XVVBu3jsXr8YZ7M+L2I1PwksoT4Qnxu/TewbParQfj+ymk29Dr6Gvi5q0r7AqLE9rSpbPgAAAAAAAIA/AACAPwAAAABkO989lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSx2GlIwBQ5R0lFKULg=="
|
42 |
+
},
|
43 |
+
"_episode_num": 1013,
|
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:": "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"
|
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 False False\n 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 False False\n False False False False True]",
|
63 |
+
"_shape": [
|
64 |
+
29
|
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 -inf -inf -inf -inf -inf -inf\n 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 inf inf 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 -inf -inf -inf -inf -inf -inf\n 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 inf inf 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 True True]",
|
77 |
+
"bounded_above": "[ True True True True True True True True]",
|
78 |
+
"_shape": [
|
79 |
+
8
|
80 |
+
],
|
81 |
+
"low": "[-1. -1. -1. -1. -1. -1. -1. -1.]",
|
82 |
+
"high": "[1. 1. 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 0x7cdbcc43a440>",
|
102 |
+
"add": "<function ReplayBuffer.add at 0x7cdbcc43a4d0>",
|
103 |
+
"sample": "<function ReplayBuffer.sample at 0x7cdbcc43a560>",
|
104 |
+
"_get_samples": "<function ReplayBuffer._get_samples at 0x7cdbcc43a5f0>",
|
105 |
+
"_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x7cdbcc43a680>)>",
|
106 |
+
"__abstractmethods__": "frozenset()",
|
107 |
+
"_abc_impl": "<_abc._abc_data object at 0x7cdbcc5b4200>"
|
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": -8.0,
|
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-AntBulletEnv-v0/ent_coef_optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c8aad7684158b298b218de556548afbdf3d1c0066598f09922726731b3eedbb
|
3 |
+
size 1940
|
tqc-AntBulletEnv-v0/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e84f5ae6b0bbc2403b2d027a7f65094681c6adba8a51c3ba6196921f00d6b3b1
|
3 |
+
size 2846969
|
tqc-AntBulletEnv-v0/pytorch_variables.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0a864c5c64ff9f5ff632ff09509e4d3bd9ece362756753d890003bb774ddab1
|
3 |
+
size 1180
|
tqc-AntBulletEnv-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:a342a75e5b7df4acfc3cd1d01c1f108ae05798d7e9b4a36086a1371a1af14412
|
3 |
+
size 48224
|