Hugging Face's logo

gokuuu
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
gokuuu commited on
Commit
cc38762
•
1 Parent(s): b1a4511

Initial commit

Browse files
Files changed (9) 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.pth +1 -1
  7. replay.mp4 +0 -0
  8. results.json +1 -1
  9. 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: 124.00 +/- 38.00
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -71,8 +71,8 @@ OrderedDict([('batch_size', 32),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
- ('learning_starts', 100000),
75
- ('n_timesteps', 1000.0),
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: 29.00 +/- 64.30
20
  name: mean_reward
21
  verified: false
22
  ---
 
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
+ ('learning_starts', 200000),
75
+ ('n_timesteps', 100000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -56,7 +56,7 @@
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
- - 3360390238
60
  - - storage
61
  - null
62
  - - study_name
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 861573382
60
  - - storage
61
  - null
62
  - - study_name
config.yml CHANGED
@@ -16,9 +16,9 @@
16
  - - learning_rate
17
  - 0.0001
18
  - - learning_starts
19
- - 100000
20
  - - n_timesteps
21
- - 1000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
16
  - - learning_rate
17
  - 0.0001
18
  - - learning_starts
19
+ - 200000
20
  - - n_timesteps
21
+ - 100000.0
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 sha256:7da6f0621d365e808255c4503826ae445da48de14d9b9008c727795ad7b35b71
3
- size 13711607
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d19603ea4da8b27b1f1b7c0600c9d1210e22f05bf4811288fe54ad9538753bb
3
+ size 13715667
dqn-SpaceInvadersNoFrameskip-v4/data CHANGED
The diff for this file is too large to render. See raw diff
 
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0451278ca0661f6f7dc9c151673fdfd3da44b0476782086e4c03a732d3686eda
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d22884e67476bed9e4636c1f3eb86306439bc9054ac692192fe7643a20e1b389
3
  size 13505370
replay.mp4 CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
 
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 124.0, "std_reward": 38.0, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-09-22T12:20:18.390444"}
 
1
+ {"mean_reward": 29.0, "std_reward": 64.29618962271404, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-09-22T12:31:54.332734"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4098103b99ff46a5aaa1d27a249e781b900a7d0a315394eb0cb3aa1984fc741f
3
- size 247
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2735e62f969daa74d0cf5c62b471e991d7d6cf41bf7aeb431df3f96f747594be
3
+ size 5679