Hugging Face's logo

eLarry
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
eLarry commited on
Commit
c7e968c
•
1 Parent(s): 0eaae53

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 +1 -1
  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: 161.50 +/- 126.25
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -70,9 +70,9 @@ OrderedDict([('batch_size', 64),
70
  ('exploration_fraction', 0.1),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
- ('learning_rate', 0.0005),
74
  ('learning_starts', 100000),
75
- ('n_timesteps', 10000000.0),
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: 275.50 +/- 83.08
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
- - 2324369168
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 338643570
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -14,11 +14,11 @@
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 0.0005
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 10000000.0
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:c17b68ee70fd003e385aba94de068c2f7e8062eff5ecf34e8e032297c464e350
3
  size 13719681
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42701d4240f29243e14bbe28f18951f79f287f92bdefbc461de901314a5b124c
3
  size 13719681
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:a60a2a4741a1897a60dc2a3fa42e53709e1a5b25e11dd522d0066d0bd6ff2c55
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2cbea93aa998a3114d7b0e19fbd3e65edc311a58b95199b7b2a09052fe1b3ed
3
  size 623
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9cc870509bfc56d1bb825a7532f30e2066277567d61314d5ed96b8b61922b958
3
  size 13504745
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07e2b50ea8ced85ecdd4c42e7a6bc8064ad83284f36f9cc548e677d33ee2b78a
3
  size 13504745
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e407ed3bb7cc2c77d2f5f6824aedc3aeddb92e6f4f96e4aa93182da40d32cb5
3
- size 249277
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:699e69dfc5d1237c8ce5a4e20c14b02f97ae97b39dbbcc0f679e7b84864ceb6b
3
+ size 262996
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 161.5, "std_reward": 126.25470288270454, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-02-18T18:56:43.805608"}
 
1
+ {"mean_reward": 275.5, "std_reward": 83.07978093375065, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-02-18T22:25:03.141582"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75555d360f236540170c43dfc3c9b2318e950f5b8d6e84deb6c01b64307223c7
3
- size 5926
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3924d70c8ccd08b59ab2531490ced438a14ddd7254779412161f882a4fc1187
3
+ size 5867