chirbard commited on
Commit
a143521
1 Parent(s): 378bb0c

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: 190.00 +/- 99.30
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: 512.50 +/- 269.25
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
- - 461960798
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 91556732
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:a33213acd351d2fa342325a4ad450e7a91ed6bef5d0390ed95b46da53ad1bc13
3
- size 13715089
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f4beac505fb9b612ab7817d9f541a4f04d25cb305e0db72b02e793bf64a0099
3
+ size 27220214
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 sha256:2ece312723a67dbe6de4b54a35e21f59431fa8cc3e261753cd6c2eb546342511
3
+ size 13506236
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8350ada63b94fb22b62ee3a84dff53eb21367bc35a84af57984bb7ce444db4dd
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91fcdc382c7d45df4d874b959c459b97d59a52ee54c0b6d6badacd3b65c1f5d6
3
  size 13505370
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:53d082465cb6fb7abc3e7dc4e789fb6449a6b352159d4b202ea4cf822616102d
3
- size 286288
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:626275b7f43ccbedbeaf017b8d680ea0d798b7cb73cf4f38cde5deaa35afd40c
3
+ size 236568
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 190.0, "std_reward": 99.29753269845128, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-04-18T08:31:16.880327"}
 
1
+ {"mean_reward": 512.5, "std_reward": 269.251276691495, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-04-18T11:05:55.875833"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:465b8113f66dcb77b8813ef6f3bcb5fc4215053a035daca367d5f61d5cca3e1d
3
- size 5640
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7622d77e9551ff56f82d09ac164671dfb2546b46c3c3ad2c4101a95f7b76bb2e
3
+ size 36712