Initial commit
Browse files- .gitattributes +2 -0
- README.md +67 -0
- args.yml +65 -0
- config.yml +27 -0
- env_kwargs.yml +1 -0
- replay.mp4 +3 -0
- results.json +1 -0
- train_eval_metrics.zip +3 -0
- trpo-Ant-v3.zip +3 -0
- trpo-Ant-v3/_stable_baselines3_version +1 -0
- trpo-Ant-v3/data +102 -0
- trpo-Ant-v3/policy.optimizer.pth +3 -0
- trpo-Ant-v3/policy.pth +3 -0
- trpo-Ant-v3/pytorch_variables.pth +3 -0
- trpo-Ant-v3/system_info.txt +7 -0
- vec_normalize.pkl +3 -0
.gitattributes
CHANGED
@@ -25,3 +25,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
*.mp4 filter=lfs diff=lfs merge=lfs -text
|
29 |
+
vec_normalize.pkl filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: stable-baselines3
|
3 |
+
tags:
|
4 |
+
- Ant-v3
|
5 |
+
- deep-reinforcement-learning
|
6 |
+
- reinforcement-learning
|
7 |
+
- stable-baselines3
|
8 |
+
model-index:
|
9 |
+
- name: TRPO
|
10 |
+
results:
|
11 |
+
- metrics:
|
12 |
+
- type: mean_reward
|
13 |
+
value: 4735.93 +/- 1018.56
|
14 |
+
name: mean_reward
|
15 |
+
task:
|
16 |
+
type: reinforcement-learning
|
17 |
+
name: reinforcement-learning
|
18 |
+
dataset:
|
19 |
+
name: Ant-v3
|
20 |
+
type: Ant-v3
|
21 |
+
---
|
22 |
+
|
23 |
+
# **TRPO** Agent playing **Ant-v3**
|
24 |
+
This is a trained model of a **TRPO** agent playing **Ant-v3**
|
25 |
+
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
|
26 |
+
and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
|
27 |
+
|
28 |
+
The RL Zoo is a training framework for Stable Baselines3
|
29 |
+
reinforcement learning agents,
|
30 |
+
with hyperparameter optimization and pre-trained agents included.
|
31 |
+
|
32 |
+
## Usage (with SB3 RL Zoo)
|
33 |
+
|
34 |
+
RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
|
35 |
+
SB3: https://github.com/DLR-RM/stable-baselines3<br/>
|
36 |
+
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 utils.load_from_hub --algo trpo --env Ant-v3 -orga sb3 -f logs/
|
41 |
+
python enjoy.py --algo trpo --env Ant-v3 -f logs/
|
42 |
+
```
|
43 |
+
|
44 |
+
## Training (with the RL Zoo)
|
45 |
+
```
|
46 |
+
python train.py --algo trpo --env Ant-v3 -f logs/
|
47 |
+
# Upload the model and generate video (when possible)
|
48 |
+
python -m utils.push_to_hub --algo trpo --env Ant-v3 -f logs/ -orga sb3
|
49 |
+
```
|
50 |
+
|
51 |
+
## Hyperparameters
|
52 |
+
```python
|
53 |
+
OrderedDict([('batch_size', 128),
|
54 |
+
('cg_damping', 0.1),
|
55 |
+
('cg_max_steps', 25),
|
56 |
+
('gae_lambda', 0.95),
|
57 |
+
('gamma', 0.99),
|
58 |
+
('learning_rate', 0.001),
|
59 |
+
('n_critic_updates', 20),
|
60 |
+
('n_envs', 2),
|
61 |
+
('n_steps', 1024),
|
62 |
+
('n_timesteps', 1000000.0),
|
63 |
+
('normalize', True),
|
64 |
+
('policy', 'MlpPolicy'),
|
65 |
+
('sub_sampling_factor', 1),
|
66 |
+
('normalize_kwargs', {'norm_obs': True, 'norm_reward': False})])
|
67 |
+
```
|
args.yml
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
!!python/object/apply:collections.OrderedDict
|
2 |
+
- - - algo
|
3 |
+
- trpo
|
4 |
+
- - env
|
5 |
+
- Ant-v3
|
6 |
+
- - env_kwargs
|
7 |
+
- null
|
8 |
+
- - eval_episodes
|
9 |
+
- 20
|
10 |
+
- - eval_freq
|
11 |
+
- 50000
|
12 |
+
- - gym_packages
|
13 |
+
- []
|
14 |
+
- - hyperparams
|
15 |
+
- null
|
16 |
+
- - log_folder
|
17 |
+
- logs
|
18 |
+
- - log_interval
|
19 |
+
- 10
|
20 |
+
- - n_eval_envs
|
21 |
+
- 10
|
22 |
+
- - n_evaluations
|
23 |
+
- 20
|
24 |
+
- - n_jobs
|
25 |
+
- 1
|
26 |
+
- - n_startup_trials
|
27 |
+
- 10
|
28 |
+
- - n_timesteps
|
29 |
+
- -1
|
30 |
+
- - n_trials
|
31 |
+
- 10
|
32 |
+
- - no_optim_plots
|
33 |
+
- false
|
34 |
+
- - num_threads
|
35 |
+
- -1
|
36 |
+
- - optimization_log_path
|
37 |
+
- null
|
38 |
+
- - optimize_hyperparameters
|
39 |
+
- false
|
40 |
+
- - pruner
|
41 |
+
- median
|
42 |
+
- - sampler
|
43 |
+
- tpe
|
44 |
+
- - save_freq
|
45 |
+
- -1
|
46 |
+
- - save_replay_buffer
|
47 |
+
- false
|
48 |
+
- - seed
|
49 |
+
- 1682662646
|
50 |
+
- - storage
|
51 |
+
- null
|
52 |
+
- - study_name
|
53 |
+
- null
|
54 |
+
- - tensorboard_log
|
55 |
+
- ''
|
56 |
+
- - trained_agent
|
57 |
+
- ''
|
58 |
+
- - truncate_last_trajectory
|
59 |
+
- true
|
60 |
+
- - uuid
|
61 |
+
- false
|
62 |
+
- - vec_env
|
63 |
+
- dummy
|
64 |
+
- - verbose
|
65 |
+
- 1
|
config.yml
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
!!python/object/apply:collections.OrderedDict
|
2 |
+
- - - batch_size
|
3 |
+
- 128
|
4 |
+
- - cg_damping
|
5 |
+
- 0.1
|
6 |
+
- - cg_max_steps
|
7 |
+
- 25
|
8 |
+
- - gae_lambda
|
9 |
+
- 0.95
|
10 |
+
- - gamma
|
11 |
+
- 0.99
|
12 |
+
- - learning_rate
|
13 |
+
- 0.001
|
14 |
+
- - n_critic_updates
|
15 |
+
- 20
|
16 |
+
- - n_envs
|
17 |
+
- 2
|
18 |
+
- - n_steps
|
19 |
+
- 1024
|
20 |
+
- - n_timesteps
|
21 |
+
- 1000000.0
|
22 |
+
- - normalize
|
23 |
+
- true
|
24 |
+
- - policy
|
25 |
+
- MlpPolicy
|
26 |
+
- - sub_sampling_factor
|
27 |
+
- 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 sha256:0447f6a92bfb6e6ac9956cf515b2f2f387a628615954ac79b3565bf070142b9c
|
3 |
+
size 1593903
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 4735.9274755999995, "std_reward": 1018.5638586800919, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-02T13:15:47.771925"}
|
train_eval_metrics.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f0c6020640186a9aa58a4feae42c30f15782cea83e34b6a2e1c2623e85e2154b
|
3 |
+
size 134237
|
trpo-Ant-v3.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bd9a4aab5fd165f4b9c19abedfb3376ecdd513cd4c686a23890f4553109512b6
|
3 |
+
size 218861
|
trpo-Ant-v3/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.5.1a8
|
trpo-Ant-v3/data
ADDED
@@ -0,0 +1,102 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"policy_class": {
|
3 |
+
":type:": "<class 'abc.ABCMeta'>",
|
4 |
+
":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
5 |
+
"__module__": "stable_baselines3.common.policies",
|
6 |
+
"__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\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 ortho_init: Whether to use or not orthogonal initialization\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 full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\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()`` 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 squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\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 ",
|
7 |
+
"__init__": "<function ActorCriticPolicy.__init__ at 0x7f086fa2e950>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f086fa2e9e0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f086fa2ea70>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f086fa2eb00>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f086fa2eb90>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f086fa2ec20>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f086fa2ecb0>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f086fa2ed40>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f086fa2edd0>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f086fa2ee60>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f086fa2eef0>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f086fa7f840>"
|
20 |
+
},
|
21 |
+
"verbose": 1,
|
22 |
+
"policy_kwargs": {},
|
23 |
+
"observation_space": {
|
24 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
25 |
+
":serialized:": "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",
|
26 |
+
"dtype": "float64",
|
27 |
+
"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 -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 -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 -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]",
|
28 |
+
"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 inf inf inf inf inf inf inf inf\n 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 inf inf inf inf inf inf inf inf\n 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 inf inf inf inf inf inf inf inf\n inf inf inf]",
|
29 |
+
"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 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 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 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 False False False False False False False False\n False False False]",
|
30 |
+
"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 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 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 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 False False False False False False False False\n False False False]",
|
31 |
+
"_np_random": null,
|
32 |
+
"_shape": [
|
33 |
+
111
|
34 |
+
]
|
35 |
+
},
|
36 |
+
"action_space": {
|
37 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
38 |
+
":serialized:": "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",
|
39 |
+
"dtype": "float32",
|
40 |
+
"low": "[-1. -1. -1. -1. -1. -1. -1. -1.]",
|
41 |
+
"high": "[1. 1. 1. 1. 1. 1. 1. 1.]",
|
42 |
+
"bounded_below": "[ True True True True True True True True]",
|
43 |
+
"bounded_above": "[ True True True True True True True True]",
|
44 |
+
"_np_random": "RandomState(MT19937)",
|
45 |
+
"_shape": [
|
46 |
+
8
|
47 |
+
]
|
48 |
+
},
|
49 |
+
"n_envs": 2,
|
50 |
+
"num_timesteps": 1001472,
|
51 |
+
"_total_timesteps": 1000000,
|
52 |
+
"_num_timesteps_at_start": 0,
|
53 |
+
"seed": 0,
|
54 |
+
"action_noise": null,
|
55 |
+
"start_time": 1640694203.6096184,
|
56 |
+
"learning_rate": {
|
57 |
+
":type:": "<class 'function'>",
|
58 |
+
":serialized:": "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"
|
59 |
+
},
|
60 |
+
"tensorboard_log": null,
|
61 |
+
"lr_schedule": {
|
62 |
+
":type:": "<class 'function'>",
|
63 |
+
":serialized:": "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"
|
64 |
+
},
|
65 |
+
"_last_obs": null,
|
66 |
+
"_last_episode_starts": {
|
67 |
+
":type:": "<class 'numpy.ndarray'>",
|
68 |
+
":serialized:": "gASVigAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwKFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDAgAAlHSUYi4="
|
69 |
+
},
|
70 |
+
"_last_original_obs": {
|
71 |
+
":type:": "<class 'numpy.ndarray'>",
|
72 |
+
":serialized:": "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"
|
73 |
+
},
|
74 |
+
"_episode_num": 0,
|
75 |
+
"use_sde": false,
|
76 |
+
"sde_sample_freq": -1,
|
77 |
+
"_current_progress_remaining": -0.0014719999999999178,
|
78 |
+
"ep_info_buffer": {
|
79 |
+
":type:": "<class 'collections.deque'>",
|
80 |
+
":serialized:": "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"
|
81 |
+
},
|
82 |
+
"ep_success_buffer": {
|
83 |
+
":type:": "<class 'collections.deque'>",
|
84 |
+
":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
85 |
+
},
|
86 |
+
"_n_updates": 489,
|
87 |
+
"n_steps": 1024,
|
88 |
+
"gamma": 0.99,
|
89 |
+
"gae_lambda": 0.95,
|
90 |
+
"ent_coef": 0.0,
|
91 |
+
"vf_coef": 0.0,
|
92 |
+
"max_grad_norm": 0.0,
|
93 |
+
"normalize_advantage": true,
|
94 |
+
"batch_size": 128,
|
95 |
+
"cg_max_steps": 25,
|
96 |
+
"cg_damping": 0.1,
|
97 |
+
"line_search_shrinking_factor": 0.8,
|
98 |
+
"line_search_max_iter": 10,
|
99 |
+
"target_kl": 0.01,
|
100 |
+
"n_critic_updates": 20,
|
101 |
+
"sub_sampling_factor": 1
|
102 |
+
}
|
trpo-Ant-v3/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:20cf38337ef5d18d3beba81c84857049dd661038b6111536ab275e981d11448b
|
3 |
+
size 94465
|
trpo-Ant-v3/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2547032cc816d73bafedb4c83bc6cd742149b12bb55983e67a6e66840ffb8dc
|
3 |
+
size 97278
|
trpo-Ant-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
|
trpo-Ant-v3/system_info.txt
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
OS: Linux-5.13.0-44-generic-x86_64-with-debian-bullseye-sid #49~20.04.1-Ubuntu SMP Wed May 18 18:44:28 UTC 2022
|
2 |
+
Python: 3.7.10
|
3 |
+
Stable-Baselines3: 1.5.1a8
|
4 |
+
PyTorch: 1.11.0
|
5 |
+
GPU Enabled: True
|
6 |
+
Numpy: 1.21.2
|
7 |
+
Gym: 0.21.0
|
vec_normalize.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f3c2d0c53a690ea535a334b76f1c1b1d48ffc8beb61eb5652a191cd5fad20ad
|
3 |
+
size 9887
|