Il8 commited on
Commit
5f6a1d1
1 Parent(s): f828392

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: 609.50 +/- 190.58
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', 0.1),
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'),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 551.00 +/- 217.28
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', 0.2),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
+ ('learning_starts', 50000),
75
  ('n_timesteps', 1000000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
args.yml CHANGED
@@ -18,7 +18,7 @@
18
  - - hyperparams
19
  - null
20
  - - log_folder
21
- - logs/dqn/
22
  - - log_interval
23
  - -1
24
  - - max_total_trials
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 2269910377
58
  - - storage
59
  - null
60
  - - study_name
 
18
  - - hyperparams
19
  - null
20
  - - log_folder
21
+ - logs/dqn2/
22
  - - log_interval
23
  - -1
24
  - - max_total_trials
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 3328307241
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
- - 0.1
12
  - - frame_stack
13
  - 4
14
  - - gradient_steps
@@ -16,7 +16,7 @@
16
  - - learning_rate
17
  - 0.0001
18
  - - learning_starts
19
- - 100000
20
  - - n_timesteps
21
  - 1000000.0
22
  - - optimize_memory_usage
 
8
  - - exploration_final_eps
9
  - 0.01
10
  - - exploration_fraction
11
+ - 0.2
12
  - - frame_stack
13
  - 4
14
  - - gradient_steps
 
16
  - - learning_rate
17
  - 0.0001
18
  - - learning_starts
19
+ - 50000
20
  - - n_timesteps
21
  - 1000000.0
22
  - - optimize_memory_usage
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b58ac64a8fd0a7029c6d6f7682f5e97e1164f1cb8b7fb7638da0211f7dcb84d
3
- size 27224807
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9b44b5a044cf344a3794a651f7e51a5869c76b9fce21c0a74d27f66c5d127dd
3
+ size 27224806
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 sha256:0b8a5469ffe9205cf179171b6597fe07a1939ca9ea6b863ff9a996aa8d8f98a8
3
  size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:579a9890f7b839e57ba6a37cd2beb1a0e87fefa53a3fefe81c5cafbf04892e85
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:b10af34688f91044b4099f9a67c72dbefef40851991304a623891aed29cc0451
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c29446c85c7e446c686f3d0e1b41c68879ce149c75917fa88513f85f8c7ae9b5
3
  size 13504937
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e795949c4d7b2a9892390b34ff288d1a974ab548056155e66109268983a0100
3
- size 190353
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb64e7a3451fc46b83ead86ae51993bafc106fa2b6a2a1e8a61e9fac26575dfa
3
+ size 200297
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 609.5, "std_reward": 190.58397099441495, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-02-09T13:42:37.482099"}
 
1
+ {"mean_reward": 551.0, "std_reward": 217.27632176562636, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-02-10T10:18:13.871982"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:847623cb3bb852ec07f88b44f4ace996eaa3160146c5e38ff59801e0843fa60d
3
- size 38000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8467541f036e4f6d08498e52cb76a1cc3c2e7232219f97ef6121218a6890c5d
3
+ size 35617