maldred commited on
Commit
019dc5f
1 Parent(s): bb374b4

Initial commit

Browse files
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
- value: 329.00 +/- 157.97
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -72,7 +72,7 @@ OrderedDict([('batch_size', 32),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
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: 603.50 +/- 110.02
20
  name: mean_reward
21
  verified: false
22
  ---
 
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
- - 422921262
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 3759916678
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 100000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
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 sha256:39bfb3e7ff026dc6037ed0c1222df63faac31fe16bd625e211b6e3be04f444d3
3
- size 13715007
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70cce7e2d9ada00ad9c45ec279107280928644fdcc147cca20f93f3d69ec3123
3
+ size 27220132
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:e3fc84919e676e2bdcaa04814c7dfa2b7625d8d53a818418c6db25771364db93
3
- size 1120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2252e02216a450922835f7e994e792ccf31d596d6b00833065d0fcb0b326898f
3
+ size 13506236
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:548305e233669b6ff886dafbf205906fcfc1674b4727d824ecee276710ebd841
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:469da3807fa2ad8d5666d6dedfd913d918e1e7f9473058d1c4bb26cc2d5dd97e
3
  size 13505370
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99e402fa68302f9262ebfd7be784ce6ff6785b68f25d4aa3a86e2c515a7bbb11
3
- size 242628
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b5540f6ee62014613f5779f462191b7777e4703acd4753f46deeb30c137d3cc
3
+ size 217248
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 329.0, "std_reward": 157.96835126062436, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-01-02T18:18:52.590103"}
 
1
+ {"mean_reward": 603.5, "std_reward": 110.02386104841077, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-01-02T19:34:24.460766"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:95d27c211186719c19d2d01d2a0fd23033178acf22569ca89c8e56274b7234af
3
- size 5820
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d84344c4fc88d02b541a2d978f0346cd174f3c6b49e350e36f24ac3dddd999b
3
+ size 38183