Quentin Gallouédec
commited on
Commit
•
5742880
1
Parent(s):
364fe2c
Initial commit
Browse files- .gitattributes +1 -0
- README.md +75 -0
- args.yml +83 -0
- config.yml +19 -0
- env_kwargs.yml +1 -0
- replay.mp4 +3 -0
- results.json +1 -0
- td3-Hopper-v3.zip +3 -0
- td3-Hopper-v3/_stable_baselines3_version +1 -0
- td3-Hopper-v3/actor.optimizer.pth +3 -0
- td3-Hopper-v3/critic.optimizer.pth +3 -0
- td3-Hopper-v3/data +121 -0
- td3-Hopper-v3/policy.pth +3 -0
- td3-Hopper-v3/pytorch_variables.pth +3 -0
- td3-Hopper-v3/system_info.txt +7 -0
- train_eval_metrics.zip +3 -0
.gitattributes
CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
35 |
+
*.mp4 filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: stable-baselines3
|
3 |
+
tags:
|
4 |
+
- Hopper-v3
|
5 |
+
- deep-reinforcement-learning
|
6 |
+
- reinforcement-learning
|
7 |
+
- stable-baselines3
|
8 |
+
model-index:
|
9 |
+
- name: TD3
|
10 |
+
results:
|
11 |
+
- task:
|
12 |
+
type: reinforcement-learning
|
13 |
+
name: reinforcement-learning
|
14 |
+
dataset:
|
15 |
+
name: Hopper-v3
|
16 |
+
type: Hopper-v3
|
17 |
+
metrics:
|
18 |
+
- type: mean_reward
|
19 |
+
value: 3450.33 +/- 14.87
|
20 |
+
name: mean_reward
|
21 |
+
verified: false
|
22 |
+
---
|
23 |
+
|
24 |
+
# **TD3** Agent playing **Hopper-v3**
|
25 |
+
This is a trained model of a **TD3** agent playing **Hopper-v3**
|
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 td3 --env Hopper-v3 -orga qgallouedec -f logs/
|
47 |
+
python -m rl_zoo3.enjoy --algo td3 --env Hopper-v3 -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 td3 --env Hopper-v3 -orga qgallouedec -f logs/
|
53 |
+
python -m rl_zoo3.enjoy --algo td3 --env Hopper-v3 -f logs/
|
54 |
+
```
|
55 |
+
|
56 |
+
## Training (with the RL Zoo)
|
57 |
+
```
|
58 |
+
python -m rl_zoo3.train --algo td3 --env Hopper-v3 -f logs/
|
59 |
+
# Upload the model and generate video (when possible)
|
60 |
+
python -m rl_zoo3.push_to_hub --algo td3 --env Hopper-v3 -f logs/ -orga qgallouedec
|
61 |
+
```
|
62 |
+
|
63 |
+
## Hyperparameters
|
64 |
+
```python
|
65 |
+
OrderedDict([('batch_size', 256),
|
66 |
+
('gradient_steps', 1),
|
67 |
+
('learning_rate', 0.0003),
|
68 |
+
('learning_starts', 10000),
|
69 |
+
('n_timesteps', 1000000.0),
|
70 |
+
('noise_std', 0.1),
|
71 |
+
('noise_type', 'normal'),
|
72 |
+
('policy', 'MlpPolicy'),
|
73 |
+
('train_freq', 1),
|
74 |
+
('normalize', False)])
|
75 |
+
```
|
args.yml
ADDED
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
!!python/object/apply:collections.OrderedDict
|
2 |
+
- - - algo
|
3 |
+
- td3
|
4 |
+
- - conf_file
|
5 |
+
- null
|
6 |
+
- - device
|
7 |
+
- auto
|
8 |
+
- - env
|
9 |
+
- Hopper-v3
|
10 |
+
- - env_kwargs
|
11 |
+
- null
|
12 |
+
- - eval_episodes
|
13 |
+
- 20
|
14 |
+
- - eval_freq
|
15 |
+
- 25000
|
16 |
+
- - gym_packages
|
17 |
+
- []
|
18 |
+
- - hyperparams
|
19 |
+
- null
|
20 |
+
- - log_folder
|
21 |
+
- logs
|
22 |
+
- - log_interval
|
23 |
+
- -1
|
24 |
+
- - max_total_trials
|
25 |
+
- null
|
26 |
+
- - n_eval_envs
|
27 |
+
- 5
|
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 |
+
- -1
|
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 |
+
- 361241903
|
58 |
+
- - storage
|
59 |
+
- null
|
60 |
+
- - study_name
|
61 |
+
- null
|
62 |
+
- - tensorboard_log
|
63 |
+
- runs/Hopper-v3__td3__361241903__1676765475
|
64 |
+
- - track
|
65 |
+
- true
|
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 |
+
- openrlbenchmark
|
78 |
+
- - wandb_project_name
|
79 |
+
- sb3
|
80 |
+
- - wandb_tags
|
81 |
+
- []
|
82 |
+
- - yaml_file
|
83 |
+
- null
|
config.yml
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
!!python/object/apply:collections.OrderedDict
|
2 |
+
- - - batch_size
|
3 |
+
- 256
|
4 |
+
- - gradient_steps
|
5 |
+
- 1
|
6 |
+
- - learning_rate
|
7 |
+
- 0.0003
|
8 |
+
- - learning_starts
|
9 |
+
- 10000
|
10 |
+
- - n_timesteps
|
11 |
+
- 1000000.0
|
12 |
+
- - noise_std
|
13 |
+
- 0.1
|
14 |
+
- - noise_type
|
15 |
+
- normal
|
16 |
+
- - policy
|
17 |
+
- MlpPolicy
|
18 |
+
- - train_freq
|
19 |
+
- 1
|
env_kwargs.yml
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{}
|
replay.mp4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:99ea8153f1b4d2b2ab20b7b4ef48a58320940af010a8ed194f1560f8ff55e9d3
|
3 |
+
size 1508512
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 3450.3252839, "std_reward": 14.87010102439793, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-28T17:32:32.160804"}
|
td3-Hopper-v3.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fdbc8e05390ad2923e906aef5d0a7078e9f621f05d53df5bf9f4f27951e32622
|
3 |
+
size 6115040
|
td3-Hopper-v3/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.8.0a6
|
td3-Hopper-v3/actor.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6cf8eff9f3fd812caa86a9f1d5d26ed41f65e43d9308be4b1a14f0ff8fbf4910
|
3 |
+
size 1012911
|
td3-Hopper-v3/critic.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c91a4e24d3ce2b9f4d4909d6ca17668b0f0a228044456f67c7ca63f4965bda6
|
3 |
+
size 2035001
|
td3-Hopper-v3/data
ADDED
@@ -0,0 +1,121 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"policy_class": {
|
3 |
+
":type:": "<class 'abc.ABCMeta'>",
|
4 |
+
":serialized:": "gAWVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLnRkMy5wb2xpY2llc5SMCVREM1BvbGljeZSTlC4=",
|
5 |
+
"__module__": "stable_baselines3.td3.policies",
|
6 |
+
"__doc__": "\n Policy class (with both actor and critic) for TD3.\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 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 TD3Policy.__init__ at 0x7f90f0df0af0>",
|
8 |
+
"_build": "<function TD3Policy._build at 0x7f90f0df0b80>",
|
9 |
+
"_get_constructor_parameters": "<function TD3Policy._get_constructor_parameters at 0x7f90f0df0c10>",
|
10 |
+
"make_actor": "<function TD3Policy.make_actor at 0x7f90f0df0ca0>",
|
11 |
+
"make_critic": "<function TD3Policy.make_critic at 0x7f90f0df0d30>",
|
12 |
+
"forward": "<function TD3Policy.forward at 0x7f90f0df0dc0>",
|
13 |
+
"_predict": "<function TD3Policy._predict at 0x7f90f0df0e50>",
|
14 |
+
"set_training_mode": "<function TD3Policy.set_training_mode at 0x7f90f0df0ee0>",
|
15 |
+
"__abstractmethods__": "frozenset()",
|
16 |
+
"_abc_impl": "<_abc._abc_data object at 0x7f90f12fcec0>"
|
17 |
+
},
|
18 |
+
"verbose": 1,
|
19 |
+
"policy_kwargs": {},
|
20 |
+
"observation_space": {
|
21 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
22 |
+
":serialized:": "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",
|
23 |
+
"dtype": "float64",
|
24 |
+
"_shape": [
|
25 |
+
11
|
26 |
+
],
|
27 |
+
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf]",
|
28 |
+
"high": "[inf inf inf inf inf inf inf inf inf inf inf]",
|
29 |
+
"bounded_below": "[False False False False False False False False False False False]",
|
30 |
+
"bounded_above": "[False False False False False False False False False False False]",
|
31 |
+
"_np_random": null
|
32 |
+
},
|
33 |
+
"action_space": {
|
34 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
35 |
+
":serialized:": "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",
|
36 |
+
"dtype": "float32",
|
37 |
+
"_shape": [
|
38 |
+
3
|
39 |
+
],
|
40 |
+
"low": "[-1. -1. -1.]",
|
41 |
+
"high": "[1. 1. 1.]",
|
42 |
+
"bounded_below": "[ True True True]",
|
43 |
+
"bounded_above": "[ True True True]",
|
44 |
+
"_np_random": "RandomState(MT19937)"
|
45 |
+
},
|
46 |
+
"n_envs": 1,
|
47 |
+
"num_timesteps": 1000000,
|
48 |
+
"_total_timesteps": 1000000,
|
49 |
+
"_num_timesteps_at_start": 0,
|
50 |
+
"seed": 0,
|
51 |
+
"action_noise": {
|
52 |
+
":type:": "<class 'stable_baselines3.common.noise.NormalActionNoise'>",
|
53 |
+
":serialized:": "gAWVCgEAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5ub2lzZZSMEU5vcm1hbEFjdGlvbk5vaXNllJOUKYGUfZQojANfbXWUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWGAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJmOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwOFlIwBQ5R0lFKUjAZfc2lnbWGUaAgolhgAAAAAAAAAmpmZmZmZuT+amZmZmZm5P5qZmZmZmbk/lGgPSwOFlGgTdJRSlHViLg==",
|
54 |
+
"_mu": "[0. 0. 0.]",
|
55 |
+
"_sigma": "[0.1 0.1 0.1]"
|
56 |
+
},
|
57 |
+
"start_time": 1676765478541973316,
|
58 |
+
"learning_rate": {
|
59 |
+
":type:": "<class 'function'>",
|
60 |
+
":serialized:": "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"
|
61 |
+
},
|
62 |
+
"tensorboard_log": "runs/Hopper-v3__td3__361241903__1676765475/Hopper-v3",
|
63 |
+
"lr_schedule": {
|
64 |
+
":type:": "<class 'function'>",
|
65 |
+
":serialized:": "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"
|
66 |
+
},
|
67 |
+
"_last_obs": null,
|
68 |
+
"_last_episode_starts": {
|
69 |
+
":type:": "<class 'numpy.ndarray'>",
|
70 |
+
":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
|
71 |
+
},
|
72 |
+
"_last_original_obs": {
|
73 |
+
":type:": "<class 'numpy.ndarray'>",
|
74 |
+
":serialized:": "gAWVzQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZYAAAAAAAAAKopTqzGW/M/3oOgWm2ahr/Bp/y+VTjgv82Rp6BJmIY/2quY7npK6T8XJydvEFcCQJiJ5KtL/vq/sL9mNpULc78KmcfC13fxP72Q6BEjpdS/9HohBhuXwb+UjAVudW1weZSMBWR0eXBllJOUjAJmOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLC4aUjAFDlHSUUpQu"
|
75 |
+
},
|
76 |
+
"_episode_num": 3330,
|
77 |
+
"use_sde": false,
|
78 |
+
"sde_sample_freq": -1,
|
79 |
+
"_current_progress_remaining": 0.0,
|
80 |
+
"ep_info_buffer": {
|
81 |
+
":type:": "<class 'collections.deque'>",
|
82 |
+
":serialized:": "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"
|
83 |
+
},
|
84 |
+
"ep_success_buffer": {
|
85 |
+
":type:": "<class 'collections.deque'>",
|
86 |
+
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
87 |
+
},
|
88 |
+
"_n_updates": 990000,
|
89 |
+
"buffer_size": 1,
|
90 |
+
"batch_size": 256,
|
91 |
+
"learning_starts": 10000,
|
92 |
+
"tau": 0.005,
|
93 |
+
"gamma": 0.99,
|
94 |
+
"gradient_steps": 1,
|
95 |
+
"optimize_memory_usage": false,
|
96 |
+
"replay_buffer_class": {
|
97 |
+
":type:": "<class 'abc.ABCMeta'>",
|
98 |
+
":serialized:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
|
99 |
+
"__module__": "stable_baselines3.common.buffers",
|
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 0x7f90f0ded5e0>",
|
102 |
+
"add": "<function ReplayBuffer.add at 0x7f90f0ded670>",
|
103 |
+
"sample": "<function ReplayBuffer.sample at 0x7f90f0ded700>",
|
104 |
+
"_get_samples": "<function ReplayBuffer._get_samples at 0x7f90f0ded790>",
|
105 |
+
"__abstractmethods__": "frozenset()",
|
106 |
+
"_abc_impl": "<_abc._abc_data object at 0x7f90f0def100>"
|
107 |
+
},
|
108 |
+
"replay_buffer_kwargs": {},
|
109 |
+
"train_freq": {
|
110 |
+
":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
|
111 |
+
":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
|
112 |
+
},
|
113 |
+
"use_sde_at_warmup": false,
|
114 |
+
"policy_delay": 2,
|
115 |
+
"target_noise_clip": 0.5,
|
116 |
+
"target_policy_noise": 0.2,
|
117 |
+
"actor_batch_norm_stats": [],
|
118 |
+
"critic_batch_norm_stats": [],
|
119 |
+
"actor_batch_norm_stats_target": [],
|
120 |
+
"critic_batch_norm_stats_target": []
|
121 |
+
}
|
td3-Hopper-v3/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:962d729560a08265da26d405863a9bb06b21cde51a0cb03faee6f50468f4bb7f
|
3 |
+
size 3045753
|
td3-Hopper-v3/pytorch_variables.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
|
3 |
+
size 431
|
td3-Hopper-v3/system_info.txt
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
- OS: Linux-5.19.0-32-generic-x86_64-with-glibc2.35 # 33~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Mon Jan 30 17:03:34 UTC 2
|
2 |
+
- Python: 3.9.12
|
3 |
+
- Stable-Baselines3: 1.8.0a6
|
4 |
+
- PyTorch: 1.13.1+cu117
|
5 |
+
- GPU Enabled: True
|
6 |
+
- Numpy: 1.24.1
|
7 |
+
- Gym: 0.21.0
|
train_eval_metrics.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80d52d26609fbc5d4b005521db66e7a480300d73d7804a9c52e711d337ef099f
|
3 |
+
size 103775
|