Quentin Gallouédec
commited on
Commit
•
20e331b
1
Parent(s):
a67f73c
Initial commit
Browse files- .gitattributes +1 -0
- README.md +79 -0
- args.yml +83 -0
- config.yml +25 -0
- env_kwargs.yml +1 -0
- ppo-SeaquestNoFrameskip-v4.zip +3 -0
- ppo-SeaquestNoFrameskip-v4/_stable_baselines3_version +1 -0
- ppo-SeaquestNoFrameskip-v4/data +0 -0
- ppo-SeaquestNoFrameskip-v4/policy.optimizer.pth +3 -0
- ppo-SeaquestNoFrameskip-v4/policy.pth +3 -0
- ppo-SeaquestNoFrameskip-v4/pytorch_variables.pth +3 -0
- ppo-SeaquestNoFrameskip-v4/system_info.txt +7 -0
- replay.mp4 +3 -0
- results.json +1 -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 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: stable-baselines3
|
3 |
+
tags:
|
4 |
+
- SeaquestNoFrameskip-v4
|
5 |
+
- deep-reinforcement-learning
|
6 |
+
- reinforcement-learning
|
7 |
+
- stable-baselines3
|
8 |
+
model-index:
|
9 |
+
- name: PPO
|
10 |
+
results:
|
11 |
+
- task:
|
12 |
+
type: reinforcement-learning
|
13 |
+
name: reinforcement-learning
|
14 |
+
dataset:
|
15 |
+
name: SeaquestNoFrameskip-v4
|
16 |
+
type: SeaquestNoFrameskip-v4
|
17 |
+
metrics:
|
18 |
+
- type: mean_reward
|
19 |
+
value: 1816.00 +/- 14.97
|
20 |
+
name: mean_reward
|
21 |
+
verified: false
|
22 |
+
---
|
23 |
+
|
24 |
+
# **PPO** Agent playing **SeaquestNoFrameskip-v4**
|
25 |
+
This is a trained model of a **PPO** agent playing **SeaquestNoFrameskip-v4**
|
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 ppo --env SeaquestNoFrameskip-v4 -orga qgallouedec -f logs/
|
47 |
+
python -m rl_zoo3.enjoy --algo ppo --env SeaquestNoFrameskip-v4 -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 ppo --env SeaquestNoFrameskip-v4 -orga qgallouedec -f logs/
|
53 |
+
python -m rl_zoo3.enjoy --algo ppo --env SeaquestNoFrameskip-v4 -f logs/
|
54 |
+
```
|
55 |
+
|
56 |
+
## Training (with the RL Zoo)
|
57 |
+
```
|
58 |
+
python -m rl_zoo3.train --algo ppo --env SeaquestNoFrameskip-v4 -f logs/
|
59 |
+
# Upload the model and generate video (when possible)
|
60 |
+
python -m rl_zoo3.push_to_hub --algo ppo --env SeaquestNoFrameskip-v4 -f logs/ -orga qgallouedec
|
61 |
+
```
|
62 |
+
|
63 |
+
## Hyperparameters
|
64 |
+
```python
|
65 |
+
OrderedDict([('batch_size', 256),
|
66 |
+
('clip_range', 'lin_0.1'),
|
67 |
+
('ent_coef', 0.01),
|
68 |
+
('env_wrapper',
|
69 |
+
['stable_baselines3.common.atari_wrappers.AtariWrapper']),
|
70 |
+
('frame_stack', 4),
|
71 |
+
('learning_rate', 'lin_2.5e-4'),
|
72 |
+
('n_envs', 8),
|
73 |
+
('n_epochs', 4),
|
74 |
+
('n_steps', 128),
|
75 |
+
('n_timesteps', 10000000.0),
|
76 |
+
('policy', 'CnnPolicy'),
|
77 |
+
('vf_coef', 0.5),
|
78 |
+
('normalize', False)])
|
79 |
+
```
|
args.yml
ADDED
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
!!python/object/apply:collections.OrderedDict
|
2 |
+
- - - algo
|
3 |
+
- ppo
|
4 |
+
- - conf_file
|
5 |
+
- null
|
6 |
+
- - device
|
7 |
+
- auto
|
8 |
+
- - env
|
9 |
+
- SeaquestNoFrameskip-v4
|
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 |
+
- 3287718523
|
58 |
+
- - storage
|
59 |
+
- null
|
60 |
+
- - study_name
|
61 |
+
- null
|
62 |
+
- - tensorboard_log
|
63 |
+
- runs/SeaquestNoFrameskip-v4__ppo__3287718523__1675438075
|
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 |
+
- qgallouedec
|
78 |
+
- - wandb_project_name
|
79 |
+
- sb3-iqn
|
80 |
+
- - wandb_tags
|
81 |
+
- []
|
82 |
+
- - yaml_file
|
83 |
+
- null
|
config.yml
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
!!python/object/apply:collections.OrderedDict
|
2 |
+
- - - batch_size
|
3 |
+
- 256
|
4 |
+
- - clip_range
|
5 |
+
- lin_0.1
|
6 |
+
- - ent_coef
|
7 |
+
- 0.01
|
8 |
+
- - env_wrapper
|
9 |
+
- - stable_baselines3.common.atari_wrappers.AtariWrapper
|
10 |
+
- - frame_stack
|
11 |
+
- 4
|
12 |
+
- - learning_rate
|
13 |
+
- lin_2.5e-4
|
14 |
+
- - n_envs
|
15 |
+
- 8
|
16 |
+
- - n_epochs
|
17 |
+
- 4
|
18 |
+
- - n_steps
|
19 |
+
- 128
|
20 |
+
- - n_timesteps
|
21 |
+
- 10000000.0
|
22 |
+
- - policy
|
23 |
+
- CnnPolicy
|
24 |
+
- - vf_coef
|
25 |
+
- 0.5
|
env_kwargs.yml
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{}
|
ppo-SeaquestNoFrameskip-v4.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3628128db396867272a30b8c62f85218822abc55e665007761ddb5de26d7f976
|
3 |
+
size 20519136
|
ppo-SeaquestNoFrameskip-v4/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.8.0a6
|
ppo-SeaquestNoFrameskip-v4/data
ADDED
The diff for this file is too large to render.
See raw diff
|
|
ppo-SeaquestNoFrameskip-v4/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:888232bc3944379e6c2f388d2ed8eec666aef213c0fc676a048f5fce73a00d06
|
3 |
+
size 13560761
|
ppo-SeaquestNoFrameskip-v4/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:423c1dfbf92807002c8c7e39e2ac7952f38316a6315c1dc0564d43ebe6c68ae7
|
3 |
+
size 6782465
|
ppo-SeaquestNoFrameskip-v4/pytorch_variables.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
|
3 |
+
size 431
|
ppo-SeaquestNoFrameskip-v4/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
|
replay.mp4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e8688991c6b5f273e15e3cf46789b6a34779817371f7f029c77e2716dbe4372e
|
3 |
+
size 163834
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 1816.0, "std_reward": 14.966629547095765, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-02-27T19:38:15.788801"}
|
train_eval_metrics.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ec7768dc6565e9138be1e96535e280aabf7e881e4f26964b7c7b53a0025be49
|
3 |
+
size 249555
|