Hugging Face's logo

PierrotLalune
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
PierrotLalune commited on
Commit
62d9b4d
•
1 Parent(s): ad37779

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: 240.00 +/- 167.79
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-05),
74
  ('learning_starts', 100000),
75
- ('n_timesteps', 900000.0),
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: 749.00 +/- 308.60
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', 5000000.0),
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
- - 3135970357
60
  - - storage
61
  - null
62
  - - study_name
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 3964520451
60
  - - storage
61
  - null
62
  - - study_name
config.yml CHANGED
@@ -14,11 +14,11 @@
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 1.0e-05
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 900000.0
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
+ - 5000000.0
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 sha256:2a6f057cffe80d975db7f25e7212a62d3c3e9a16cc1ac7175acc3fdc447df38d
3
- size 27220725
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03d72c195f9eb4c35abebb4e3c5c6b402613f926d44fa4d6015613561c63c89c
3
+ size 27220743
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 sha256:044ae73afcedf38fe6a4c77caeb1c6c575c1b520460dc2165a50a7d5939ad187
3
  size 13506172
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e98378acf270df64b357317dc5e2853cdec3fad75f3210baf6803dca7213cadc
3
  size 13506172
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:58dceb320a3827ca0aeff54923298bc33f2a4e43944d6ecb4c93542f22df95d8
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:702b928a1e7d49b43e4c68c255f42e166dfb394881fd725786d263069a640521
3
  size 13505370
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:137e6241245f603805107f3f1c5cf3584af26d4b903fb17e59702de2f16bcbd3
3
- size 230482
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47d5b611e051a7964cd040b6ce731ed18116852dda0b51afcc20a1d3cfc05b48
3
+ size 211813
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 240.0, "std_reward": 167.79451719290472, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-09-21T09:42:17.819381"}
 
1
+ {"mean_reward": 749.0, "std_reward": 308.6000648088072, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-09-21T11:31:05.219492"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e70030680714d15a08637d4453f86554ef52c1a95735655e1b00499c78a845fb
3
- size 39484
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe2ac6e7cf66809fd80d0ea57eb05827c8a2be39a6072aaf61442d6c7c4cd5db
3
+ size 50380