Hugging Face's logo

LeKyks1
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
LeKyks1 commited on
Commit
8c81631
•
1 Parent(s): 9503ef4

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: 280.00 +/- 102.10
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -67,11 +67,11 @@ OrderedDict([('batch_size', 32),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
  ('exploration_final_eps', 0.01),
70
- ('exploration_fraction', 0.11),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.001),
74
- ('learning_starts', 10000),
75
  ('n_timesteps', 100000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 182.50 +/- 139.11
20
  name: mean_reward
21
  verified: false
22
  ---
 
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
  ('exploration_final_eps', 0.01),
70
+ ('exploration_fraction', 0.1),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.001),
74
+ ('learning_starts', 5000),
75
  ('n_timesteps', 100000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 3055323658
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 3258054328
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -8,7 +8,7 @@
8
  - - exploration_final_eps
9
  - 0.01
10
  - - exploration_fraction
11
- - 0.11
12
  - - frame_stack
13
  - 4
14
  - - gradient_steps
@@ -16,7 +16,7 @@
16
  - - learning_rate
17
  - 0.001
18
  - - learning_starts
19
- - 10000
20
  - - n_timesteps
21
  - 100000.0
22
  - - optimize_memory_usage
 
8
  - - exploration_final_eps
9
  - 0.01
10
  - - exploration_fraction
11
+ - 0.1
12
  - - frame_stack
13
  - 4
14
  - - gradient_steps
 
16
  - - learning_rate
17
  - 0.001
18
  - - learning_starts
19
+ - 5000
20
  - - n_timesteps
21
  - 100000.0
22
  - - optimize_memory_usage
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3f0cc648a2923d0858303d0e5774d838b4c2d0500e564c298e72c69a8578ad56
3
- size 27220130
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21990ef3711296b5f6ae6a71fa331529b35eba5fb4f55e9d5532827928799853
3
+ size 27220128
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 sha256:38c38333e15f332e65df74e182e4ff5cfbc7f76835e9a20640eee0d8692d034b
3
  size 13506236
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15a40216c6ad3c865902f2362f2aa7e0fca1568c28fc474a01f2a85728ad1322
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:c0838eda037b3383303ecc344d9176419bc80daedde5d0ce543c884f2803af20
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8265974694b6b7015f829a39d0ccdb736536a057e626f3e90f69899a7232dcc1
3
  size 13505370
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ff5e946cc231dbe64e0c1beab938cd430c84999f8e075125322efd5f6806f850
3
- size 268534
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2419d3a14c226c37914d97be4de373a763c14a33088bf888b5b81e11cacaf2f0
3
+ size 233529
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 280.0, "std_reward": 102.10288928331069, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-02-06T01:34:34.492176"}
 
1
+ {"mean_reward": 182.5, "std_reward": 139.10877039209282, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-02-06T11:17:09.236180"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:70b899b4b7ccda4e36dc26dac005c255ae208d81b3c62591c2486029f36509d2
3
- size 4812
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b34d006a0c39e0dc7727428574f464053c1db6df637be47fad3d78a3a6e2f181
3
+ size 5033