Rudolph314 commited on
Commit
7cb25b0
1 Parent(s): ae44ba3

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: 279.00 +/- 141.93
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -68,7 +68,7 @@ OrderedDict([('batch_size', 128),
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
  ('exploration_final_eps', 0.01),
70
  ('exploration_fraction', 0.2),
71
- ('exploration_initial_eps', 0.8),
72
  ('frame_stack', 4),
73
  ('gradient_steps', 1),
74
  ('learning_rate', 0.0005),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 471.50 +/- 104.55
20
  name: mean_reward
21
  verified: false
22
  ---
 
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
  ('exploration_final_eps', 0.01),
70
  ('exploration_fraction', 0.2),
71
+ ('exploration_initial_eps', 0.3),
72
  ('frame_stack', 4),
73
  ('gradient_steps', 1),
74
  ('learning_rate', 0.0005),
args.yml CHANGED
@@ -2,7 +2,7 @@
2
  - - - algo
3
  - dqn
4
  - - conf_file
5
- - dqn.yml
6
  - - device
7
  - auto
8
  - - env
@@ -18,7 +18,7 @@
18
  - - hyperparams
19
  - null
20
  - - log_folder
21
- - logs/
22
  - - log_interval
23
  - -1
24
  - - max_total_trials
@@ -38,7 +38,7 @@
38
  - - no_optim_plots
39
  - false
40
  - - num_threads
41
- - -1
42
  - - optimization_log_path
43
  - null
44
  - - optimize_hyperparameters
@@ -50,11 +50,11 @@
50
  - - sampler
51
  - tpe
52
  - - save_freq
53
- - -1
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 3441574639
58
  - - storage
59
  - null
60
  - - study_name
@@ -64,7 +64,7 @@
64
  - - track
65
  - false
66
  - - trained_agent
67
- - ''
68
  - - truncate_last_trajectory
69
  - true
70
  - - uuid
 
2
  - - - algo
3
  - dqn
4
  - - conf_file
5
+ - dqn_resume.yaml
6
  - - device
7
  - auto
8
  - - env
 
18
  - - hyperparams
19
  - null
20
  - - log_folder
21
+ - logs
22
  - - log_interval
23
  - -1
24
  - - max_total_trials
 
38
  - - no_optim_plots
39
  - false
40
  - - num_threads
41
+ - 4
42
  - - optimization_log_path
43
  - null
44
  - - optimize_hyperparameters
 
50
  - - sampler
51
  - tpe
52
  - - save_freq
53
+ - 10000
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 978951721
58
  - - storage
59
  - null
60
  - - study_name
 
64
  - - track
65
  - false
66
  - - trained_agent
67
+ - logs/dqn/SpaceInvadersNoFrameskip-v4_1/SpaceInvadersNoFrameskip-v4.zip
68
  - - truncate_last_trajectory
69
  - true
70
  - - uuid
config.yml CHANGED
@@ -10,7 +10,7 @@
10
  - - exploration_fraction
11
  - 0.2
12
  - - exploration_initial_eps
13
- - 0.8
14
  - - frame_stack
15
  - 4
16
  - - gradient_steps
 
10
  - - exploration_fraction
11
  - 0.2
12
  - - exploration_initial_eps
13
+ - 0.3
14
  - - frame_stack
15
  - 4
16
  - - gradient_steps
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:da2f9907257f7bc2030e01db7d265c146967fb4ae373027d9d3c22e5cd411a12
3
- size 27219177
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fe6c817182d1c5595fec9ad5d13c07184faea49b0161208be2aa4f3f8f22ad1
3
+ size 27218602
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:b1af54039a8fa89b73c77ac969c44d9c4d7cb75da4e3993d158991dd10583fd8
3
- size 13506236
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0ca28f76e3229f3a464f3411b81c8a562c7b8f3e9aec056db3f3734724034e4
3
+ size 13505852
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b6779c4bbb850b5496130efbcac7f6c305d0e5402cef2a164e1600093717cdb6
3
- size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:036d2ad15b56794e8ea19851567c7264083379fede1498edc9e85b5d4d7d4243
3
+ size 13505178
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -2,7 +2,7 @@
2
  - Python: 3.10.12
3
  - Stable-Baselines3: 2.3.0
4
  - PyTorch: 2.2.1+cu121
5
- - GPU Enabled: True
6
  - Numpy: 1.25.2
7
  - Cloudpickle: 2.2.1
8
  - Gymnasium: 0.29.1
 
2
  - Python: 3.10.12
3
  - Stable-Baselines3: 2.3.0
4
  - PyTorch: 2.2.1+cu121
5
+ - GPU Enabled: False
6
  - Numpy: 1.25.2
7
  - Cloudpickle: 2.2.1
8
  - Gymnasium: 0.29.1
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:85d65b28ac6e79cf508ccea4e006c3b1397ba20fb086169339707c16d6586d06
3
- size 233056
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:419c2f9fb71741168caa346a1832b7b79c9802c89cb9a4fbfcb382ad23754380
3
+ size 227198
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 279.0, "std_reward": 141.92955999368138, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-04-12T03:04:38.419620"}
 
1
+ {"mean_reward": 471.5, "std_reward": 104.54783594125705, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-04-12T05:04:32.695147"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:745fecfb5fd94724a45c31500593dfb169ea6111d134f2d25f9c96842b932043
3
- size 34341
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a5f5c1742373638e3b84b0ce2bcb9de7dbbdee6103a9cb305f2875c988fed97
3
+ size 31208