Hugging Face's logo

NicolasYn
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
NicolasYn commited on
Commit
9d76904
•
1 Parent(s): 58c59c8

Initial commit

Browse files
Files changed (10) hide show
  1. README.md +3 -3
  2. args.yml +1 -1
  3. config.yml +2 -2
  4. dqn-SpaceInvadersNoFrameskip-v4.zip +2 -2
  5. dqn-SpaceInvadersNoFrameskip-v4/data +0 -0
  6. dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth +2 -2
  7. dqn-SpaceInvadersNoFrameskip-v4/policy.pth +1 -1
  8. replay.mp4 +2 -2
  9. results.json +1 -1
  10. train_eval_metrics.zip +2 -2
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
- value: 29.00 +/- 64.30
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -70,9 +70,9 @@ OrderedDict([('batch_size', 32),
70
  ('exploration_fraction', 0.1),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
- ('learning_rate', 1e-06),
74
  ('learning_starts', 100000),
75
- ('n_timesteps', 100000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 537.50 +/- 132.59
20
  name: mean_reward
21
  verified: false
22
  ---
 
70
  ('exploration_fraction', 0.1),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
+ ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
+ ('n_timesteps', 1000000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 434965887
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 2108180424
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -14,11 +14,11 @@
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 1.0e-06
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 100000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
+ - 0.0001
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:b2b36a1db875f7e0818c013bf532659741beac2804deefe7b335b491a98163d4
3
- size 13715083
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d835f2e071f349ac166398ec94085ad5b4cdb1d7c142fce86131d53ecf24c13
3
+ size 27220208
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:c1f3b836bd5d42486a268ff007163ab7fddb9054f9656d4a7efaad53c15e95a8
3
- size 1120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:681e7f0ffa9ab48fab2fd81c8e73583cae674fa7d977cf349b23bf63ac70259b
3
+ size 13506236
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:effe66aa67894a73bec75bc7fe43a11b39660c2f831b3c1be400d696b9dccde4
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ce787d6f37abe88f7f1a79b3641b386a45776c95cefc9aaa54cd63b3b6a07ca
3
  size 13505370
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cae3de750f432875df42a4011aeedbc220ba38b313576b27b5dbc3ebf8a98d59
3
- size 294896
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1aeed3c28e5c8654099e3d3c97c7d386e2465030e14b746e6a39aae04f61742e
3
+ size 250577
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 29.0, "std_reward": 64.29618962271404, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-03-14T18:09:20.676719"}
 
1
+ {"mean_reward": 537.5, "std_reward": 132.5943060617612, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-03-16T11:27:06.746289"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e91d38683d466e4a18871d0e67066c1056519d9aef7962f849dde6a8362e6e22
3
- size 5481
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4aeeef177cbdb29008af0b51018ce86c2a3f90d21228b2b3b907241d4f1edad2
3
+ size 35635