loupzeur commited on
Commit
d7be120
1 Parent(s): 1906ecc

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: 5.00 +/- 7.07
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', 10000.0),
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: 599.50 +/- 239.78
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
- - 3413035713
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 51678649
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 10000.0
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:cc6fc9e692f470018a2b776382bb3acc261586c8b8d9015c32cdf274dd56a6c9
3
- size 13710204
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73888614e7aa979487a8df92e789d67c2c867ef134527c9f6725c0ec51fedbfb
3
+ size 27218493
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 sha256:0b69a6cb94f8a9599ea4291f66c0618fbf541f7509cd0bdc82e64322acea359b
3
- size 687
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa4bfd8876564453eb86929ff8cc0aa7436c4ab96c32d00c1b41bd2e5f92d0cb
3
+ size 13505739
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99141e18acdbf9f0ff5dafd128a46900d6e79c82bbe01d5ec891f1dac8406974
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de1522ff2777e0044d902227a41f75028779e545c5ed797c249886aaa83b9e4b
3
  size 13504937
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3db13127af1afff79a46340c2dcb1019924e473abb0fcb413073b8546932fd7c
3
- size 294075
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4f68a692099a2a1f8c3c20034f015be7da930c7e4a6f9b16e0823b1122800bd
3
+ size 239767
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 5.0, "std_reward": 7.0710678118654755, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-09-14T15:42:40.852095"}
 
1
+ {"mean_reward": 599.5, "std_reward": 239.7754157539926, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-09-14T17:01:36.346105"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:239f1825e2aaceaae12dce7f13c7f711016ec1724565921bdde59d368e5d9f6b
3
- size 671
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91c072e072ad2861f02d6955c1c59f2259b1289b3f7a296a77dba14d13d1cde1
3
+ size 35769