Initial commit
Browse files- .gitattributes +2 -0
- README.md +63 -0
- args.yml +65 -0
- ars-Walker2d-v3.zip +3 -0
- ars-Walker2d-v3/_stable_baselines3_version +1 -0
- ars-Walker2d-v3/data +412 -0
- ars-Walker2d-v3/policy.pth +3 -0
- ars-Walker2d-v3/pytorch_variables.pth +3 -0
- ars-Walker2d-v3/system_info.txt +7 -0
- config.yml +19 -0
- env_kwargs.yml +1 -0
- replay.mp4 +3 -0
- results.json +1 -0
- train_eval_metrics.zip +3 -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 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: stable-baselines3
|
3 |
+
tags:
|
4 |
+
- Walker2d-v3
|
5 |
+
- deep-reinforcement-learning
|
6 |
+
- reinforcement-learning
|
7 |
+
- stable-baselines3
|
8 |
+
model-index:
|
9 |
+
- name: ARS
|
10 |
+
results:
|
11 |
+
- metrics:
|
12 |
+
- type: mean_reward
|
13 |
+
value: 2958.36 +/- 195.43
|
14 |
+
name: mean_reward
|
15 |
+
task:
|
16 |
+
type: reinforcement-learning
|
17 |
+
name: reinforcement-learning
|
18 |
+
dataset:
|
19 |
+
name: Walker2d-v3
|
20 |
+
type: Walker2d-v3
|
21 |
+
---
|
22 |
+
|
23 |
+
# **ARS** Agent playing **Walker2d-v3**
|
24 |
+
This is a trained model of a **ARS** agent playing **Walker2d-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 ars --env Walker2d-v3 -orga sb3 -f logs/
|
41 |
+
python enjoy.py --algo ars --env Walker2d-v3 -f logs/
|
42 |
+
```
|
43 |
+
|
44 |
+
## Training (with the RL Zoo)
|
45 |
+
```
|
46 |
+
python train.py --algo ars --env Walker2d-v3 -f logs/
|
47 |
+
# Upload the model and generate video (when possible)
|
48 |
+
python -m utils.push_to_hub --algo ars --env Walker2d-v3 -f logs/ -orga sb3
|
49 |
+
```
|
50 |
+
|
51 |
+
## Hyperparameters
|
52 |
+
```python
|
53 |
+
OrderedDict([('alive_bonus_offset', -1),
|
54 |
+
('delta_std', 0.025),
|
55 |
+
('learning_rate', 0.03),
|
56 |
+
('n_delta', 40),
|
57 |
+
('n_envs', 16),
|
58 |
+
('n_timesteps', 75000000.0),
|
59 |
+
('n_top', 30),
|
60 |
+
('normalize', 'dict(norm_obs=True, norm_reward=False)'),
|
61 |
+
('policy', 'LinearPolicy'),
|
62 |
+
('normalize_kwargs', {'norm_obs': True, 'norm_reward': False})])
|
63 |
+
```
|
args.yml
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
!!python/object/apply:collections.OrderedDict
|
2 |
+
- - - algo
|
3 |
+
- ars
|
4 |
+
- - env
|
5 |
+
- Walker2d-v3
|
6 |
+
- - env_kwargs
|
7 |
+
- null
|
8 |
+
- - eval_episodes
|
9 |
+
- 20
|
10 |
+
- - eval_freq
|
11 |
+
- 100000
|
12 |
+
- - gym_packages
|
13 |
+
- []
|
14 |
+
- - hyperparams
|
15 |
+
- n_envs: 16
|
16 |
+
- - log_folder
|
17 |
+
- rl-trained-agents/
|
18 |
+
- - log_interval
|
19 |
+
- 10
|
20 |
+
- - n_eval_envs
|
21 |
+
- 5
|
22 |
+
- - n_evaluations
|
23 |
+
- 20
|
24 |
+
- - n_jobs
|
25 |
+
- 1
|
26 |
+
- - n_startup_trials
|
27 |
+
- 10
|
28 |
+
- - n_timesteps
|
29 |
+
- 10000000
|
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 |
+
- 2869363972
|
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
|
ars-Walker2d-v3.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9bf98712c3e4f16d420e2cb5eddf2e427f050605bd854b75da07ae13331eb208
|
3 |
+
size 21500
|
ars-Walker2d-v3/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.5.1a8
|
ars-Walker2d-v3/data
ADDED
@@ -0,0 +1,412 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"policy_class": {
|
3 |
+
":type:": "<class 'abc.ABCMeta'>",
|
4 |
+
":serialized:": "gASVMAAAAAAAAACMGHNiM19jb250cmliLmFycy5wb2xpY2llc5SMD0FSU0xpbmVhclBvbGljeZSTlC4=",
|
5 |
+
"__module__": "sb3_contrib.ars.policies",
|
6 |
+
"__doc__": "\n Linear policy network for ARS.\n\n :param observation_space: The observation space of the environment\n :param action_space: The action space of the environment\n :param with_bias: With or without bias on the output\n :param squash_output: For continuous actions, whether the output is squashed\n or not using a ``tanh()`` function. If not squashed with tanh the output will instead be clipped.\n ",
|
7 |
+
"__init__": "<function ARSLinearPolicy.__init__ at 0x7fe139d8c7a0>",
|
8 |
+
"__abstractmethods__": "frozenset()",
|
9 |
+
"_abc_impl": "<_abc_data object at 0x7fe13a04e870>"
|
10 |
+
},
|
11 |
+
"verbose": 1,
|
12 |
+
"policy_kwargs": {},
|
13 |
+
"observation_space": {
|
14 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
15 |
+
":serialized:": "gASVpQIAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMA2xvd5SMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlGgGjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSxGFlGgKiUOIAAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/5R0lGKMBGhpZ2iUaBBoEksAhZRoFIeUUpQoSwFLEYWUaAqJQ4gAAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/lHSUYowNYm91bmRlZF9iZWxvd5RoEGgSSwCFlGgUh5RSlChLAUsRhZRoB4wCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDEQAAAAAAAAAAAAAAAAAAAAAAlHSUYowNYm91bmRlZF9hYm92ZZRoEGgSSwCFlGgUh5RSlChLAUsRhZRoKIlDEQAAAAAAAAAAAAAAAAAAAAAAlHSUYowKX25wX3JhbmRvbZROjAZfc2hhcGWUSxGFlHViLg==",
|
16 |
+
"dtype": "float64",
|
17 |
+
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf]",
|
18 |
+
"high": "[inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf]",
|
19 |
+
"bounded_below": "[False False False False False False False False False False False False\n False False False False False]",
|
20 |
+
"bounded_above": "[False False False False False False False False False False False False\n False False False False False]",
|
21 |
+
"_np_random": null,
|
22 |
+
"_shape": [
|
23 |
+
17
|
24 |
+
]
|
25 |
+
},
|
26 |
+
"action_space": {
|
27 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
28 |
+
":serialized:": "gASVPwwAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMA2xvd5SMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlGgGjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwaFlGgKiUMYAACAvwAAgL8AAIC/AACAvwAAgL8AAIC/lHSUYowEaGlnaJRoEGgSSwCFlGgUh5RSlChLAUsGhZRoColDGAAAgD8AAIA/AACAPwAAgD8AAIA/AACAP5R0lGKMDWJvdW5kZWRfYmVsb3eUaBBoEksAhZRoFIeUUpQoSwFLBoWUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGKJQwYBAQEBAQGUdJRijA1ib3VuZGVkX2Fib3ZllGgQaBJLAIWUaBSHlFKUKEsBSwaFlGgoiUMGAQEBAQEBlHSUYowKX25wX3JhbmRvbZSMFG51bXB5LnJhbmRvbS5fcGlja2xllIwSX19yYW5kb21zdGF0ZV9jdG9ylJOUjAdNVDE5OTM3lIWUUpR9lCiMDWJpdF9nZW5lcmF0b3KUaDiMBXN0YXRllH2UKIwDa2V5lGgQaBJLAIWUaBSHlFKUKEsBTXAChZRoB4wCdTSUiYiHlFKUKEsDaAtOTk5K/////0r/////SwB0lGKJQsAJAAAAAACAU8KznIcDtZNy7Ktb6Oay8s+2gdrVBu9hoTFNoGu1zNkT5hifdJx5L8ilG4DEeQFJng9D5F3gGJOSE1XM1EopZNIIlb400J5EcnoD8K2/CnObez7pYLEG2nUDRQtufdYWausENGaDt/P1pS9p70JjQ7Vc98J3UsxGRDctCIlu0I6ud/sYtoBPe575TzLsEti5jl6FqRnKrj12LWcrQoCexe7HH/UiAV1LzyQPzBlSZERXmHCdCvUSF7XpWt47xP9BzzqxX7aH3TPYWImqos1/ez/JlLdsD0MfMZl9G2CQq7cHHRlM3sj7jroA9c+pGt4l/iAGpRb80HbjwU71ykPTAVp531BXrc2qmIU6z9Fh4TAPx7fZ1kVF+L1Irlou+4Ckky7Ys59nB7KkciTI+N5jlb62ybZt0+ZWgIA6LKLvdx/mTQtB4k1aplT/C7L9/ybKCFn2quN/7YlIkxoH1U0xdabG6rgOrR+SHMmvUwvtKB+19Ibb07mSgVQyjNAvnyADPJf3pkxylZtn7f/OVpWEaWfl6BcLwy0grrEgUK+H+8P8XWMuBginXgwzn3sy4+ZOlr45op6TtuqX0Knz/SySGDlBIK8JqKObzB6fGt+ovJHEM8KlL4veKwkLkuuMWBaex3FBdWskry5qhslxMgnk2thh8DaXmAfbuI8j0SqHMW1kleITi9ekfXx/eSi5hX1GjA/M62Zixuay1H8zH9VjsTRcGacyJ0vh1hNReDFoNsXFbLfLqaIvbLDQjY7T289ZXsupvAxu2GVTbqWst+ckPPzwH7vLikULC+weAKwxarqm+ugAXgyz774meHOsvQYuu18nvrrunjZWDvwaKuYohEwUfSnpotE9XhX99yUTc8sGPQidTfXkzm/t8MWP8it4l4VSEgDLn8GW8t2DAh8EwFa/KOGoZEGjYqZ2IMA70E+F2LqgaZlQLFMONTIx3yuN5F2e1MT4v2wdBRK9R+lGMpxIiNldyOwwxLDBTRDMhd7APidmDwQBnvaIecKFa95btwHkRBEUT5g++/I0DDg685EX4OMO2YtTPqM3PQluS4puEhAQRVukNGSh4gYDgcBPKZl4ThNf+G+E7El9fmWJcP39Sifw6Mn+GEisM1RhHY05XZHUv5W4r8kD2jSLMY+IIL2+LtQrW7it7y28+sEicLoEfYOky9ZJF6l0fR+sXEawf+REH9LvtRJ4yzfxr7KisNpr1axv1ae5CDXS+XTzuOG/BJnHvt8arnY1XWH9SdkCOeok6MI8GBCtjTCxJ5JbpI5J0i0A66mJaRW9LMfP6Cil3/cVRQ9uN2KTtV3o7rJwY4XCnj7DJmqrUwofDDl7Ek0PoN7w0Hh8YHOy8qhPw7V8ALdjZn7eYtjCQIldQvHbM1I73RtCLQvQGFMXUCJ022pGRqTvZX5XWSizqbgX6TJmI6LDF9wcpYealB7cDwelfqdpzHRmyjRbIX9b+w4uj//aDRgP2SgiOAq/D/9/0SbgK/E0FQyclhNVAkbKwXhAxKGczpvJow0mFFUAt/5fT5KAsmQTAt8p0FsrGMDTfk4RzZgqZSm+ihVRS371Tx3twpGA1goo/AIfJh8slJC3hkR1OGCN7LAPGCwbM9rHlKSU4uuhJiff196h9q1kPMld6989MfKLVkvCl7ofCRurPUW46ceJKE951sQD1v8cK0HK1JmuBTCXAelCUCIFNLGk3tMXNVmuuFF3o3xb4V4T1IAYIfBdyEVHhIIZOE/JEY79daQw8njYEtQ6YwZ6kNCBYfrjq2OglITcRdwDmINL42ro6HnbWgLZQ8Ce/EiPVBtWHwhvGUHK1FNONzRzXgT1zKEg+WAigeuK4QVIxdITM4YvUyYvpQJuJd+xGD1no7BYIKXdV4aDlsRnWSMmS+zTyTvC0+TgBMCNpMvdChjaB/XTrMVsm0vgPmCYswn067MTYWfm5oCqqmNciqoRfFL2O2mxFT1VMcKDrxHBdBUhSG5UmAerx86KAEytbsCbn6OOj8Y02VwVynzXd0WJfLioeGMZISM1eneWfTc1mQ6CpdDxJqUmU86/KsBL3Bb0S2NAqFysFJZKxDwLej8xz+xH8IxEHzlkiiNH+2IIq0663FAwi6wg6dgcryDqQ+lNDwn898nylrcYShigDrtrFBNezKx3ZjpkPCnPUeQB4hJUrYCUJy5CyytC/x1UsByKez/aSNEWnlWnzYdJf2PoKL0YfmaR3KpXzi9ax3BHPgk1cdmgdVkqevFJ0DUdTBFQj/mhaKqcaT0rKJLgy/11AhWW4nX7+kAdgR0b1iAseI0TbMDtohBuqqUZfqMfUKsdI8v2aeUd0+IqOjPBFe7TZRC7OUYmf789SRTpw9gst4tzx7tLap8JnFt2keKhqd3vBgqpvlsxvx0DcPC+bo/qIldKiAn5D7TPjeWLzJ1gmpk1mVKOyWOv/ZzlRTfe8yEsMsRcgdPxbOuxLjlOwo1uFh9NjHoOz/xbnI62I49ZzT59GUCNtAL74UqjlRoyXZ5ELEjhTn+F5fYfEkY2TnSsgKO4Wwb/xD41S4mBL7LcUyF76ybV7Yx0L6V2QGoSfyhHFqMQJs/haLPPW18mWJb/UDl90ZN9TEzcdXvZsmCeqzCagC6YDHp3fop+5nAQSnT/Byt2j7z+6cnl/aZh6oKs5xrEMmuzpLFbXNVof9hNmX5E0DQ2M8uBqqeW95p6z8ySnOxURAO28oYWsbVyeYaNlWLZrOtIMZDRjjbecSSwMLlrBhw4mZVht4DgOQxI1+P7sPHZLMf89U+5ctf1rD0r1AXgyXjzOxKvCxWMhrz6Ah19+zal/bAIpw+0V7Pq85PRQO4UeScmMwODR8jcOfILuMmo7xXhemY/JqtOncklEaGapMeGlkiefvQkx9L5EWvLn6stI4zRP4pZXx9iOz17IKJmKOVHgCIAOiheb0bwkjNkItlfYO3LzeLLPuBDNLFg7tQu5NPWy28a4nBsE/gsyEteRvF2ECYFIOJg06dzc77IWw7o+z1Q5APxLg9uvyFniYWNuJyk7rflLCmYcg1gN657CWff8YfPr0ukKOamco94X1nFdyroxHiQlRXaP91DOqMueI1pCasyRQt0jtbWwxdEVyzP3GzUZXBWqa0xXCzwe29cxg2aiwKuuAAVfaCE/Pt1cJXq8wvliF81sMDPMbowd9+uyWuExq/e+2W3wWeV3hVofoiEySjBrJPWVJW9++UocJbC0ppNw5mtHktkZqUk6kVtUgVQ4Cj4udj/bluZzcqWjIvOCJO52M+xcQY808Ei8T/lwwS9TguuzQ3e0KR7hptgNcX1/XhCvAuUdJRijANwb3OUTXACdYwJaGFzX2dhdXNzlEsAjAVnYXVzc5RHAAAAAAAAAAB1YowGX3NoYXBllEsGhZR1Yi4=",
|
29 |
+
"dtype": "float32",
|
30 |
+
"low": "[-1. -1. -1. -1. -1. -1.]",
|
31 |
+
"high": "[1. 1. 1. 1. 1. 1.]",
|
32 |
+
"bounded_below": "[ True True True True True True]",
|
33 |
+
"bounded_above": "[ True True True True True True]",
|
34 |
+
"_np_random": "RandomState(MT19937)",
|
35 |
+
"_shape": [
|
36 |
+
6
|
37 |
+
]
|
38 |
+
},
|
39 |
+
"n_envs": 1,
|
40 |
+
"num_timesteps": 10032736,
|
41 |
+
"_total_timesteps": 10000000,
|
42 |
+
"_num_timesteps_at_start": 0,
|
43 |
+
"seed": 0,
|
44 |
+
"action_noise": null,
|
45 |
+
"start_time": 1642503798.7439346,
|
46 |
+
"learning_rate": {
|
47 |
+
":type:": "<class 'function'>",
|
48 |
+
":serialized:": "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"
|
49 |
+
},
|
50 |
+
"tensorboard_log": null,
|
51 |
+
"lr_schedule": {
|
52 |
+
":type:": "<class 'function'>",
|
53 |
+
":serialized:": "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"
|
54 |
+
},
|
55 |
+
"_last_obs": null,
|
56 |
+
"_last_episode_starts": {
|
57 |
+
":type:": "<class 'numpy.ndarray'>",
|
58 |
+
":serialized:": "gASViQAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwGFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDAQGUdJRiLg=="
|
59 |
+
},
|
60 |
+
"_last_original_obs": {
|
61 |
+
":type:": "<class 'numpy.ndarray'>",
|
62 |
+
":serialized:": "gASVEgEAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwFLEYaUaAOMBWR0eXBllJOUjAJmOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiiUOIqHm3STsP9D/8AohUsgReP+x0FqLyxV4/1BQUQNnXWD8Af5EryBQVvxCvOgCYP2M/QKhe0IDqNz8KpElGUrZTv8wDa+VnGGA/QLAidCTQFb//tV+3AR9yP5h547N/33K/Pmlac2+IbD+f34+266lyP4KvdWu1Lm0/GnK5r1WmYD9dLJ+YGb9wP5R0lGIu"
|
63 |
+
},
|
64 |
+
"_episode_num": 0,
|
65 |
+
"use_sde": false,
|
66 |
+
"sde_sample_freq": -1,
|
67 |
+
"_current_progress_remaining": 0.0038015999999999606,
|
68 |
+
"ep_info_buffer": [
|
69 |
+
{
|
70 |
+
"r": 2643.62661,
|
71 |
+
"l": 1000
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"r": 2510.853675,
|
75 |
+
"l": 1000
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"r": 2807.489659,
|
79 |
+
"l": 1000
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"r": 1094.863633,
|
83 |
+
"l": 394
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"r": 2717.115548,
|
87 |
+
"l": 1000
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"r": 2787.763485,
|
91 |
+
"l": 1000
|
92 |
+
},
|
93 |
+
{
|
94 |
+
"r": 2299.908169,
|
95 |
+
"l": 1000
|
96 |
+
},
|
97 |
+
{
|
98 |
+
"r": 1303.175779,
|
99 |
+
"l": 466
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"r": 1203.89447,
|
103 |
+
"l": 432
|
104 |
+
},
|
105 |
+
{
|
106 |
+
"r": 2859.028576,
|
107 |
+
"l": 1000
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"r": 2605.18292,
|
111 |
+
"l": 1000
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"r": 2850.029786,
|
115 |
+
"l": 1000
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"r": 614.582185,
|
119 |
+
"l": 270
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"r": 2914.719409,
|
123 |
+
"l": 1000
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"r": 2715.512378,
|
127 |
+
"l": 1000
|
128 |
+
},
|
129 |
+
{
|
130 |
+
"r": 2967.831803,
|
131 |
+
"l": 1000
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"r": 1090.888155,
|
135 |
+
"l": 367
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"r": 2454.22781,
|
139 |
+
"l": 1000
|
140 |
+
},
|
141 |
+
{
|
142 |
+
"r": 2833.815341,
|
143 |
+
"l": 1000
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"r": 1199.886324,
|
147 |
+
"l": 487
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"r": 2692.710278,
|
151 |
+
"l": 1000
|
152 |
+
},
|
153 |
+
{
|
154 |
+
"r": 2547.894208,
|
155 |
+
"l": 1000
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"r": 2598.422535,
|
159 |
+
"l": 1000
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"r": 2316.728009,
|
163 |
+
"l": 1000
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"r": 2645.499566,
|
167 |
+
"l": 1000
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"r": 2812.221989,
|
171 |
+
"l": 854
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"r": 1316.399417,
|
175 |
+
"l": 435
|
176 |
+
},
|
177 |
+
{
|
178 |
+
"r": 2811.339687,
|
179 |
+
"l": 1000
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"r": 2730.645184,
|
183 |
+
"l": 1000
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"r": 3035.001581,
|
187 |
+
"l": 1000
|
188 |
+
},
|
189 |
+
{
|
190 |
+
"r": 3099.964356,
|
191 |
+
"l": 1000
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"r": 2903.16247,
|
195 |
+
"l": 1000
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"r": 2948.21015,
|
199 |
+
"l": 1000
|
200 |
+
},
|
201 |
+
{
|
202 |
+
"r": 1333.163548,
|
203 |
+
"l": 500
|
204 |
+
},
|
205 |
+
{
|
206 |
+
"r": 2787.074651,
|
207 |
+
"l": 1000
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"r": 2851.548297,
|
211 |
+
"l": 1000
|
212 |
+
},
|
213 |
+
{
|
214 |
+
"r": 2918.011209,
|
215 |
+
"l": 935
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"r": 2501.581186,
|
219 |
+
"l": 1000
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"r": 2301.167493,
|
223 |
+
"l": 1000
|
224 |
+
},
|
225 |
+
{
|
226 |
+
"r": 2966.32929,
|
227 |
+
"l": 1000
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"r": 2113.609808,
|
231 |
+
"l": 1000
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"r": 2765.124838,
|
235 |
+
"l": 1000
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"r": 2877.857057,
|
239 |
+
"l": 1000
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"r": 3092.594273,
|
243 |
+
"l": 1000
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"r": 2828.089001,
|
247 |
+
"l": 1000
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"r": 2732.163734,
|
251 |
+
"l": 1000
|
252 |
+
},
|
253 |
+
{
|
254 |
+
"r": 2752.967511,
|
255 |
+
"l": 1000
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"r": 2795.299091,
|
259 |
+
"l": 1000
|
260 |
+
},
|
261 |
+
{
|
262 |
+
"r": 3093.438946,
|
263 |
+
"l": 1000
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"r": 2538.059627,
|
267 |
+
"l": 1000
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"r": 2626.852761,
|
271 |
+
"l": 1000
|
272 |
+
},
|
273 |
+
{
|
274 |
+
"r": 2574.515384,
|
275 |
+
"l": 1000
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"r": 2944.116395,
|
279 |
+
"l": 1000
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"r": 2744.48868,
|
283 |
+
"l": 1000
|
284 |
+
},
|
285 |
+
{
|
286 |
+
"r": 2505.193911,
|
287 |
+
"l": 1000
|
288 |
+
},
|
289 |
+
{
|
290 |
+
"r": 2771.083432,
|
291 |
+
"l": 1000
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"r": 2928.743018,
|
295 |
+
"l": 1000
|
296 |
+
},
|
297 |
+
{
|
298 |
+
"r": 2719.885468,
|
299 |
+
"l": 1000
|
300 |
+
},
|
301 |
+
{
|
302 |
+
"r": 838.296383,
|
303 |
+
"l": 445
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"r": 1225.542692,
|
307 |
+
"l": 434
|
308 |
+
},
|
309 |
+
{
|
310 |
+
"r": 1468.70781,
|
311 |
+
"l": 483
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"r": 2988.272283,
|
315 |
+
"l": 1000
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"r": 2866.526673,
|
319 |
+
"l": 1000
|
320 |
+
},
|
321 |
+
{
|
322 |
+
"r": 3081.66669,
|
323 |
+
"l": 1000
|
324 |
+
},
|
325 |
+
{
|
326 |
+
"r": 2944.297178,
|
327 |
+
"l": 1000
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"r": 2835.274789,
|
331 |
+
"l": 1000
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"r": 2287.945532,
|
335 |
+
"l": 1000
|
336 |
+
},
|
337 |
+
{
|
338 |
+
"r": 953.665782,
|
339 |
+
"l": 457
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"r": 2384.745698,
|
343 |
+
"l": 1000
|
344 |
+
},
|
345 |
+
{
|
346 |
+
"r": 2743.267387,
|
347 |
+
"l": 1000
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"r": 2795.856295,
|
351 |
+
"l": 1000
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"r": 2686.128086,
|
355 |
+
"l": 1000
|
356 |
+
},
|
357 |
+
{
|
358 |
+
"r": 2557.846575,
|
359 |
+
"l": 1000
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"r": 2726.718215,
|
363 |
+
"l": 1000
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"r": 2712.218666,
|
367 |
+
"l": 1000
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"r": 993.561116,
|
371 |
+
"l": 359
|
372 |
+
},
|
373 |
+
{
|
374 |
+
"r": 2527.171915,
|
375 |
+
"l": 1000
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"r": 2689.389025,
|
379 |
+
"l": 1000
|
380 |
+
},
|
381 |
+
{
|
382 |
+
"r": 41.25589,
|
383 |
+
"l": 71
|
384 |
+
},
|
385 |
+
{
|
386 |
+
"r": 1018.932164,
|
387 |
+
"l": 373
|
388 |
+
}
|
389 |
+
],
|
390 |
+
"ep_success_buffer": {
|
391 |
+
":type:": "<class 'collections.deque'>",
|
392 |
+
":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
393 |
+
},
|
394 |
+
"_n_updates": 195,
|
395 |
+
"n_delta": 40,
|
396 |
+
"pop_size": 80,
|
397 |
+
"delta_std_schedule": {
|
398 |
+
":type:": "<class 'function'>",
|
399 |
+
":serialized:": "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"
|
400 |
+
},
|
401 |
+
"n_eval_episodes": 1,
|
402 |
+
"n_top": 30,
|
403 |
+
"alive_bonus_offset": -1,
|
404 |
+
"zero_policy": true,
|
405 |
+
"weights": {
|
406 |
+
":type:": "<class 'torch.Tensor'>",
|
407 |
+
":serialized:": "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"
|
408 |
+
},
|
409 |
+
"processes": null,
|
410 |
+
"old_count": 10049833.001699999,
|
411 |
+
"n_params": 102
|
412 |
+
}
|
ars-Walker2d-v3/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:70e5a7edd79e28571307f1dafa79a2283c8ddd4c8d1253337272aea64154599b
|
3 |
+
size 1323
|
ars-Walker2d-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
|
ars-Walker2d-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
|
config.yml
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
!!python/object/apply:collections.OrderedDict
|
2 |
+
- - - alive_bonus_offset
|
3 |
+
- -1
|
4 |
+
- - delta_std
|
5 |
+
- 0.025
|
6 |
+
- - learning_rate
|
7 |
+
- 0.03
|
8 |
+
- - n_delta
|
9 |
+
- 40
|
10 |
+
- - n_envs
|
11 |
+
- 16
|
12 |
+
- - n_timesteps
|
13 |
+
- 75000000.0
|
14 |
+
- - n_top
|
15 |
+
- 30
|
16 |
+
- - normalize
|
17 |
+
- dict(norm_obs=True, norm_reward=False)
|
18 |
+
- - policy
|
19 |
+
- LinearPolicy
|
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 sha256:4d1b576016d8b0badf9a101a9d945464f2cdf5b525823d6724f95a6894d2879d
|
3 |
+
size 1290456
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 2958.3646949000004, "std_reward": 195.43418652984232, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-02T19:09:53.164764"}
|
train_eval_metrics.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e5475851fbb2366b7a4db21cd98f7db5025f1f1d2833ade1471aa9c2128052f3
|
3 |
+
size 33865
|
vec_normalize.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ccc879e3c7e004ff438e63b94c65259d3f313125d100ace7d579a51cb62e1b5e
|
3 |
+
size 4973
|