Hugging Face's logo

swritchie
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
swritchie commited on
Commit
36ac9ba
•
1 Parent(s): a2a66be

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: 255.00 +/- 83.82
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', 0.01),
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: 645.50 +/- 173.12
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
- - 3728929420
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 4042674555
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -14,11 +14,11 @@
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 0.01
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:c1b24bbfff7e34ea86232d9b7052bd24a3add396b644711c525e544e2b48cf5a
3
- size 13715083
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7195746b94b04c905cfea76ffda8c3989a40c356ba418d40e85144e3d7fa40f7
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 sha256:61cd6747ceef076c969d8d7ed664b97f8cdf7ef68e1fd390fa14b7acaa464011
3
- size 1120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:293e1dd945ad53c7fb92bdf5c21012e5ec5b82003448cfd97d6f9acc08dbf058
3
+ size 13506236
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:53d037e10c861ea6f66530c2c69ce97a4b1b2a8ebcad85068af42d84ab5c3917
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d28e8a94251f20fbec5d65f22de918dbe1ee1f40878d30869d04489e33e9634
3
  size 13505370
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef9a042530e70968500a3da297db07063368f5826fd06275fdb0b3231fefc2f9
3
- size 267842
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cad2bf873e543b9e9392256c46aead0dc519d4468fe9bd1590e4b58f283365f
3
+ size 253734
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 255.0, "std_reward": 83.81527307120105, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-03-22T16:45:56.349855"}
 
1
+ {"mean_reward": 645.5, "std_reward": 173.12495487364032, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-03-25T14:59:09.622902"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d534d0e35661ac9e38b4f0aba52051eb79d25fb45236577727057076b4de833
3
- size 5773
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ee23dd8048040db3152db8dc51c837ddcee9f7eb3660f0055a6993dcc79a6c1
3
+ size 37016