Initial commit
Browse files- .gitattributes +1 -0
- README.md +69 -0
- args.yml +75 -0
- config.yml +29 -0
- dqn-SpaceInvadersNoFrameskip-v4.zip +3 -0
- dqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version +1 -0
- dqn-SpaceInvadersNoFrameskip-v4/data +0 -0
- dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth +3 -0
- dqn-SpaceInvadersNoFrameskip-v4/policy.pth +3 -0
- dqn-SpaceInvadersNoFrameskip-v4/pytorch_variables.pth +3 -0
- dqn-SpaceInvadersNoFrameskip-v4/system_info.txt +7 -0
- env_kwargs.yml +1 -0
- replay.mp4 +3 -0
- results.json +1 -0
- train_eval_metrics.zip +3 -0
.gitattributes
CHANGED
@@ -25,3 +25,4 @@ 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
|
README.md
ADDED
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: stable-baselines3
|
3 |
+
tags:
|
4 |
+
- SpaceInvadersNoFrameskip-v4
|
5 |
+
- deep-reinforcement-learning
|
6 |
+
- reinforcement-learning
|
7 |
+
- stable-baselines3
|
8 |
+
model-index:
|
9 |
+
- name: DQN
|
10 |
+
results:
|
11 |
+
- metrics:
|
12 |
+
- type: mean_reward
|
13 |
+
value: 744.00 +/- 231.20
|
14 |
+
name: mean_reward
|
15 |
+
task:
|
16 |
+
type: reinforcement-learning
|
17 |
+
name: reinforcement-learning
|
18 |
+
dataset:
|
19 |
+
name: SpaceInvadersNoFrameskip-v4
|
20 |
+
type: SpaceInvadersNoFrameskip-v4
|
21 |
+
---
|
22 |
+
|
23 |
+
# **DQN** Agent playing **SpaceInvadersNoFrameskip-v4**
|
24 |
+
This is a trained model of a **DQN** agent playing **SpaceInvadersNoFrameskip-v4**
|
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 dqn --env SpaceInvadersNoFrameskip-v4 -orga XGBooster -f logs/
|
41 |
+
python enjoy.py --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
|
42 |
+
```
|
43 |
+
|
44 |
+
## Training (with the RL Zoo)
|
45 |
+
```
|
46 |
+
python train.py --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
|
47 |
+
# Upload the model and generate video (when possible)
|
48 |
+
python -m utils.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga XGBooster
|
49 |
+
```
|
50 |
+
|
51 |
+
## Hyperparameters
|
52 |
+
```python
|
53 |
+
OrderedDict([('batch_size', 32),
|
54 |
+
('buffer_size', 100000),
|
55 |
+
('env_wrapper',
|
56 |
+
['stable_baselines3.common.atari_wrappers.AtariWrapper']),
|
57 |
+
('exploration_final_eps', 0.01),
|
58 |
+
('exploration_fraction', 0.1),
|
59 |
+
('frame_stack', 4),
|
60 |
+
('gradient_steps', 1),
|
61 |
+
('learning_rate', 0.0001),
|
62 |
+
('learning_starts', 100000),
|
63 |
+
('n_timesteps', 10000000.0),
|
64 |
+
('optimize_memory_usage', True),
|
65 |
+
('policy', 'CnnPolicy'),
|
66 |
+
('target_update_interval', 1000),
|
67 |
+
('train_freq', 4),
|
68 |
+
('normalize', False)])
|
69 |
+
```
|
args.yml
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
!!python/object/apply:collections.OrderedDict
|
2 |
+
- - - algo
|
3 |
+
- dqn
|
4 |
+
- - device
|
5 |
+
- auto
|
6 |
+
- - env
|
7 |
+
- SpaceInvadersNoFrameskip-v4
|
8 |
+
- - env_kwargs
|
9 |
+
- null
|
10 |
+
- - eval_episodes
|
11 |
+
- 5
|
12 |
+
- - eval_freq
|
13 |
+
- 25000
|
14 |
+
- - gym_packages
|
15 |
+
- []
|
16 |
+
- - hyperparams
|
17 |
+
- null
|
18 |
+
- - log_folder
|
19 |
+
- logs/
|
20 |
+
- - log_interval
|
21 |
+
- -1
|
22 |
+
- - max_total_trials
|
23 |
+
- null
|
24 |
+
- - n_eval_envs
|
25 |
+
- 1
|
26 |
+
- - n_evaluations
|
27 |
+
- null
|
28 |
+
- - n_jobs
|
29 |
+
- 1
|
30 |
+
- - n_startup_trials
|
31 |
+
- 10
|
32 |
+
- - n_timesteps
|
33 |
+
- 3000000
|
34 |
+
- - n_trials
|
35 |
+
- 500
|
36 |
+
- - no_optim_plots
|
37 |
+
- false
|
38 |
+
- - num_threads
|
39 |
+
- -1
|
40 |
+
- - optimization_log_path
|
41 |
+
- null
|
42 |
+
- - optimize_hyperparameters
|
43 |
+
- false
|
44 |
+
- - pruner
|
45 |
+
- median
|
46 |
+
- - sampler
|
47 |
+
- tpe
|
48 |
+
- - save_freq
|
49 |
+
- -1
|
50 |
+
- - save_replay_buffer
|
51 |
+
- false
|
52 |
+
- - seed
|
53 |
+
- 4224715845
|
54 |
+
- - storage
|
55 |
+
- null
|
56 |
+
- - study_name
|
57 |
+
- null
|
58 |
+
- - tensorboard_log
|
59 |
+
- ''
|
60 |
+
- - track
|
61 |
+
- false
|
62 |
+
- - trained_agent
|
63 |
+
- ''
|
64 |
+
- - truncate_last_trajectory
|
65 |
+
- true
|
66 |
+
- - uuid
|
67 |
+
- false
|
68 |
+
- - vec_env
|
69 |
+
- dummy
|
70 |
+
- - verbose
|
71 |
+
- 1
|
72 |
+
- - wandb_entity
|
73 |
+
- null
|
74 |
+
- - wandb_project_name
|
75 |
+
- sb3
|
config.yml
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
!!python/object/apply:collections.OrderedDict
|
2 |
+
- - - batch_size
|
3 |
+
- 32
|
4 |
+
- - buffer_size
|
5 |
+
- 100000
|
6 |
+
- - env_wrapper
|
7 |
+
- - stable_baselines3.common.atari_wrappers.AtariWrapper
|
8 |
+
- - exploration_final_eps
|
9 |
+
- 0.01
|
10 |
+
- - exploration_fraction
|
11 |
+
- 0.1
|
12 |
+
- - frame_stack
|
13 |
+
- 4
|
14 |
+
- - gradient_steps
|
15 |
+
- 1
|
16 |
+
- - learning_rate
|
17 |
+
- 0.0001
|
18 |
+
- - learning_starts
|
19 |
+
- 100000
|
20 |
+
- - n_timesteps
|
21 |
+
- 10000000.0
|
22 |
+
- - optimize_memory_usage
|
23 |
+
- true
|
24 |
+
- - policy
|
25 |
+
- CnnPolicy
|
26 |
+
- - target_update_interval
|
27 |
+
- 1000
|
28 |
+
- - train_freq
|
29 |
+
- 4
|
dqn-SpaceInvadersNoFrameskip-v4.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7da45de3066226fcad6d33026db93793caed54c5208640ff64c5e40a5b7f2f02
|
3 |
+
size 27222203
|
dqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.5.1a7
|
dqn-SpaceInvadersNoFrameskip-v4/data
ADDED
The diff for this file is too large to render.
See raw diff
|
|
dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:696c841aef8e54318899ecd29a4b5f437e52618a7d424b1a00569c484f0f25c2
|
3 |
+
size 13503145
|
dqn-SpaceInvadersNoFrameskip-v4/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a3454b30d24b9fa09a8ae98407b7bdbcb19a9fbb03eb3a097f0cf32714f20ad8
|
3 |
+
size 13504937
|
dqn-SpaceInvadersNoFrameskip-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
|
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
OS: Linux-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022
|
2 |
+
Python: 3.7.13
|
3 |
+
Stable-Baselines3: 1.5.1a7
|
4 |
+
PyTorch: 1.11.0+cu113
|
5 |
+
GPU Enabled: True
|
6 |
+
Numpy: 1.21.6
|
7 |
+
Gym: 0.21.0
|
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 sha256:39e7b9245d644f03d76328c7c25e2f4249af0a23e07dfad96c2bda22250d616d
|
3 |
+
size 193229
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 744.0, "std_reward": 231.20121106949244, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-06-09T16:03:35.058842"}
|
train_eval_metrics.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f19df362adff6515c7b73b97ae8e34af3645e95ea95922e116f7f948327b3ec4
|
3 |
+
size 91700
|