BekirTaha commited on
Commit
58d32c7
1 Parent(s): 4b48578

Initial commit

Browse files
README.md CHANGED
@@ -10,7 +10,7 @@ model-index:
10
  results:
11
  - metrics:
12
  - type: mean_reward
13
- value: 6.50 +/- 16.29
14
  name: mean_reward
15
  task:
16
  type: reinforcement-learning
@@ -37,7 +37,7 @@ 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 Beyko7 -f logs/
41
  python enjoy.py --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
42
  ```
43
 
@@ -45,7 +45,7 @@ python enjoy.py --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
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 Beyko7
49
  ```
50
 
51
  ## Hyperparameters
@@ -60,7 +60,7 @@ OrderedDict([('batch_size', 32),
60
  ('gradient_steps', 1),
61
  ('learning_rate', 0.0001),
62
  ('learning_starts', 100000),
63
- ('n_timesteps', 100000.0),
64
  ('optimize_memory_usage', False),
65
  ('policy', 'CnnPolicy'),
66
  ('target_update_interval', 1000),
 
10
  results:
11
  - metrics:
12
  - type: mean_reward
13
+ value: 577.50 +/- 116.86
14
  name: mean_reward
15
  task:
16
  type: reinforcement-learning
 
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 BekirTaha -f logs/
41
  python enjoy.py --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
42
  ```
43
 
 
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 BekirTaha
49
  ```
50
 
51
  ## Hyperparameters
 
60
  ('gradient_steps', 1),
61
  ('learning_rate', 0.0001),
62
  ('learning_starts', 100000),
63
+ ('n_timesteps', 1000000.0),
64
  ('optimize_memory_usage', False),
65
  ('policy', 'CnnPolicy'),
66
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -50,7 +50,7 @@
50
  - - save_replay_buffer
51
  - false
52
  - - seed
53
- - 1360778605
54
  - - storage
55
  - null
56
  - - study_name
 
50
  - - save_replay_buffer
51
  - false
52
  - - seed
53
+ - 2591579120
54
  - - storage
55
  - null
56
  - - study_name
config.yml CHANGED
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 100000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 1000000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e5a4b12e457c7c3c1d7904da5b719e38ee0302db80548f4a7c5a03b768835866
3
- size 13719817
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af925d692725c249a156388936bc752be8ce0d3511da0b6628607b98e0741aa1
3
+ size 27224877
dqn-SpaceInvadersNoFrameskip-v4/data CHANGED
The diff for this file is too large to render. See raw diff
 
dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:71a21ae67866ddb856ecbb70c8ba0e04af200cc5da53fbcb90e773d87e996b31
3
- size 687
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc6245c9a909b4d6c5a9e5234b9cd728446c9a552e28d3516ffcbd78c22d11dd
3
+ size 13505739
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d8d9dfe84033df5be0afbe3d5d48fcc1811c153f995e154d6064e144bbd58a38
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:231804ff419f91b457fba65028100f56605ab88734d06aacac9f50f2e928fa2d
3
  size 13504937
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fec26970276c80c00636ff43ee53dfe8e2e18fb4695a48055e8a79c88e18cdca
3
- size 256433
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f486acd318d14610f31453bd31c9ccb8c6a79e3a59bb7cd56490fc01ba78b81e
3
+ size 191591
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 6.5, "std_reward": 16.28649747490233, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-08-02T13:34:58.754177"}
 
1
+ {"mean_reward": 577.5, "std_reward": 116.85995892520243, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-08-03T07:41:19.220815"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:628daf96029cc8ce9c26184f660fbde05de90ac5274d4873ac47f46cd005eb09
3
- size 5739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eae0a6123f93268f5f39f8a9a1e62bdc4ff7ad5e4a48152d283aeab404f845df
3
+ size 37081