Hugging Face's logo

hemantjuyal
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
hemantjuyal commited on
Commit
8999840
•
1 Parent(s): 340562f

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 +1 -1
  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: 310.50 +/- 108.22
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', 20000),
75
- ('n_timesteps', 200000),
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: 329.00 +/- 157.97
20
  name: mean_reward
21
  verified: false
22
  ---
 
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
+ ('learning_starts', 10000),
75
+ ('n_timesteps', 100000),
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
- - 3302337778
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 413707798
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -16,9 +16,9 @@
16
  - - learning_rate
17
  - 0.0001
18
  - - learning_starts
19
- - 20000
20
  - - n_timesteps
21
- - 200000
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
16
  - - learning_rate
17
  - 0.0001
18
  - - learning_starts
19
+ - 10000
20
  - - n_timesteps
21
+ - 100000
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 sha256:69338fa513c4955b4ea0acd05a2df6f1792ef0769ca8ba22318f796e79d49d37
3
- size 27220209
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f37de1fa41fd4bea710d454b346de36c3e013db921aadfafed4e0500cebeecae
3
+ size 27217560
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 sha256:3ee1860f53d81ca616bff2660acb87a26e9fa21e7042b63e14dcf37755662415
3
  size 13505852
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba40060d82e35e60984257e228013a4b2bc832105f305cdd521ba52d94115978
3
  size 13505852
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:83fe73184e7a9136b349edd19f0998bad81d96008530bd9216bd25aad03cc381
3
  size 13505178
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:853d965484f8a6c4889f72a0248cde3176c2c78eb35ae83eedd51b0eaa325290
3
  size 13505178
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f36fd31e8a3471020aebccedd20ed3e54b50ccae6c8f846c9e950e168ca766af
3
- size 271780
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1220fd2663a829192a2b709c767eb2debf32246e6f8d3b5838a5840975ff8d0
3
+ size 242623
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 310.5, "std_reward": 108.22314909482166, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-06-22T12:26:06.725977"}
 
1
+ {"mean_reward": 329.0, "std_reward": 157.96835126062436, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-06-22T12:42:09.575495"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1702b2ef6335232af01f942c4910e824f0173be44a48fb148427dd415b7f348a
3
- size 3629
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07bcdb77f697e72c8e3b4988e930d906350a499c77966305133cf094525cc1af
3
+ size 996