kaiosinimbu
commited on
Commit
•
4dfee99
1
Parent(s):
191ac44
Initial commit
Browse files- README.md +13 -13
- args.yml +2 -2
- config.yml +1 -1
- dqn-BreakoutNoFrameskip-v4.zip +3 -0
- dqn-BreakoutNoFrameskip-v4/_stable_baselines3_version +1 -0
- dqn-BreakoutNoFrameskip-v4/data +0 -0
- dqn-BreakoutNoFrameskip-v4/policy.optimizer.pth +3 -0
- dqn-BreakoutNoFrameskip-v4/policy.pth +3 -0
- dqn-BreakoutNoFrameskip-v4/pytorch_variables.pth +3 -0
- dqn-BreakoutNoFrameskip-v4/system_info.txt +7 -0
- replay.mp4 +2 -2
- results.json +1 -1
- train_eval_metrics.zip +2 -2
README.md
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
---
|
2 |
library_name: stable-baselines3
|
3 |
tags:
|
4 |
-
-
|
5 |
- deep-reinforcement-learning
|
6 |
- reinforcement-learning
|
7 |
- stable-baselines3
|
@@ -12,17 +12,17 @@ model-index:
|
|
12 |
type: reinforcement-learning
|
13 |
name: reinforcement-learning
|
14 |
dataset:
|
15 |
-
name:
|
16 |
-
type:
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
-
value:
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
23 |
|
24 |
-
# **DQN** Agent playing **
|
25 |
-
This is a trained model of a **DQN** agent playing **
|
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 |
|
@@ -38,21 +38,21 @@ SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
|
|
38 |
|
39 |
```
|
40 |
# Download model and save it into the logs/ folder
|
41 |
-
python -m rl_zoo3.load_from_hub --algo dqn --env
|
42 |
-
python enjoy.py --algo dqn --env
|
43 |
```
|
44 |
|
45 |
If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
|
46 |
```
|
47 |
-
python -m rl_zoo3.load_from_hub --algo dqn --env
|
48 |
-
rl_zoo3 enjoy --algo dqn --env
|
49 |
```
|
50 |
|
51 |
## Training (with the RL Zoo)
|
52 |
```
|
53 |
-
python train.py --algo dqn --env
|
54 |
# Upload the model and generate video (when possible)
|
55 |
-
python -m rl_zoo3.push_to_hub --algo dqn --env
|
56 |
```
|
57 |
|
58 |
## Hyperparameters
|
@@ -67,7 +67,7 @@ OrderedDict([('batch_size', 32),
|
|
67 |
('gradient_steps', 1),
|
68 |
('learning_rate', 0.0001),
|
69 |
('learning_starts', 100000),
|
70 |
-
('n_timesteps',
|
71 |
('optimize_memory_usage', False),
|
72 |
('policy', 'CnnPolicy'),
|
73 |
('target_update_interval', 1000),
|
|
|
1 |
---
|
2 |
library_name: stable-baselines3
|
3 |
tags:
|
4 |
+
- BreakoutNoFrameskip-v4
|
5 |
- deep-reinforcement-learning
|
6 |
- reinforcement-learning
|
7 |
- stable-baselines3
|
|
|
12 |
type: reinforcement-learning
|
13 |
name: reinforcement-learning
|
14 |
dataset:
|
15 |
+
name: BreakoutNoFrameskip-v4
|
16 |
+
type: BreakoutNoFrameskip-v4
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
+
value: 47.20 +/- 13.51
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
23 |
|
24 |
+
# **DQN** Agent playing **BreakoutNoFrameskip-v4**
|
25 |
+
This is a trained model of a **DQN** agent playing **BreakoutNoFrameskip-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 |
|
|
|
38 |
|
39 |
```
|
40 |
# Download model and save it into the logs/ folder
|
41 |
+
python -m rl_zoo3.load_from_hub --algo dqn --env BreakoutNoFrameskip-v4 -orga kaiosinimbu -f logs/
|
42 |
+
python enjoy.py --algo dqn --env BreakoutNoFrameskip-v4 -f logs/
|
43 |
```
|
44 |
|
45 |
If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
|
46 |
```
|
47 |
+
python -m rl_zoo3.load_from_hub --algo dqn --env BreakoutNoFrameskip-v4 -orga kaiosinimbu -f logs/
|
48 |
+
rl_zoo3 enjoy --algo dqn --env BreakoutNoFrameskip-v4 -f logs/
|
49 |
```
|
50 |
|
51 |
## Training (with the RL Zoo)
|
52 |
```
|
53 |
+
python train.py --algo dqn --env BreakoutNoFrameskip-v4 -f logs/
|
54 |
# Upload the model and generate video (when possible)
|
55 |
+
python -m rl_zoo3.push_to_hub --algo dqn --env BreakoutNoFrameskip-v4 -f logs/ -orga kaiosinimbu
|
56 |
```
|
57 |
|
58 |
## Hyperparameters
|
|
|
67 |
('gradient_steps', 1),
|
68 |
('learning_rate', 0.0001),
|
69 |
('learning_starts', 100000),
|
70 |
+
('n_timesteps', 500000.0),
|
71 |
('optimize_memory_usage', False),
|
72 |
('policy', 'CnnPolicy'),
|
73 |
('target_update_interval', 1000),
|
args.yml
CHANGED
@@ -6,7 +6,7 @@
|
|
6 |
- - device
|
7 |
- auto
|
8 |
- - env
|
9 |
-
-
|
10 |
- - env_kwargs
|
11 |
- null
|
12 |
- - eval_episodes
|
@@ -54,7 +54,7 @@
|
|
54 |
- - save_replay_buffer
|
55 |
- false
|
56 |
- - seed
|
57 |
-
-
|
58 |
- - storage
|
59 |
- null
|
60 |
- - study_name
|
|
|
6 |
- - device
|
7 |
- auto
|
8 |
- - env
|
9 |
+
- BreakoutNoFrameskip-v4
|
10 |
- - env_kwargs
|
11 |
- null
|
12 |
- - eval_episodes
|
|
|
54 |
- - save_replay_buffer
|
55 |
- false
|
56 |
- - seed
|
57 |
+
- 1317383280
|
58 |
- - storage
|
59 |
- null
|
60 |
- - study_name
|
config.yml
CHANGED
@@ -18,7 +18,7 @@
|
|
18 |
- - learning_starts
|
19 |
- 100000
|
20 |
- - n_timesteps
|
21 |
-
-
|
22 |
- - optimize_memory_usage
|
23 |
- false
|
24 |
- - policy
|
|
|
18 |
- - learning_starts
|
19 |
- 100000
|
20 |
- - n_timesteps
|
21 |
+
- 500000.0
|
22 |
- - optimize_memory_usage
|
23 |
- false
|
24 |
- - policy
|
dqn-BreakoutNoFrameskip-v4.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d7ae43bf8ef4fe00c806cab699327fb84a775ec7809c61861d9cc6b8bd855e49
|
3 |
+
size 27208401
|
dqn-BreakoutNoFrameskip-v4/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.6.2
|
dqn-BreakoutNoFrameskip-v4/data
ADDED
The diff for this file is too large to render.
See raw diff
|
|
dqn-BreakoutNoFrameskip-v4/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d49a384027d947233a9744f1c102f95f3d333fc1f12337b69f6012965a7e2651
|
3 |
+
size 13497547
|
dqn-BreakoutNoFrameskip-v4/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a1066457d7bbee64840bb86c4c6c98d72177eae8a65eaf5f937a7a8d76e9c3b
|
3 |
+
size 13496745
|
dqn-BreakoutNoFrameskip-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-BreakoutNoFrameskip-v4/system_info.txt
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
OS: Linux-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022
|
2 |
+
Python: 3.8.15
|
3 |
+
Stable-Baselines3: 1.6.2
|
4 |
+
PyTorch: 1.12.1+cu113
|
5 |
+
GPU Enabled: True
|
6 |
+
Numpy: 1.21.6
|
7 |
+
Gym: 0.21.0
|
replay.mp4
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4425d8f04e4832a4ac4d89814f01b75d2f69942abd5b9159138e7685ffb758fc
|
3 |
+
size 77950
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 47.2, "std_reward": 13.51147660324363, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-06T16:37:02.036241"}
|
train_eval_metrics.zip
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:45951ddaf7d28df1c2f1c8a777847753945d831e86d06e9b9194864320daf2e5
|
3 |
+
size 32318
|