Hugging Face's logo

ledmands
/
dqn-Pacman-v5_kaggle_test4

Reinforcement Learning
stable-baselines3
ALE/Pacman-v5
deep-reinforcement-learning
Eval Results
Model card Files Community
ledmands commited on
Commit
c850154
•
1 Parent(s): ca0a628

Initial commit

Browse files
Files changed (7) hide show
  1. README.md +1 -1
  2. args.yml +6 -6
  3. config.yml +1 -1
  4. dqn-ALE-Pacman-v5.zip +2 -2
  5. dqn-ALE-Pacman-v5/data +0 -0
  6. results.json +1 -1
  7. train_eval_metrics.zip +2 -2
README.md CHANGED
@@ -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),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
 
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
+ ('n_timesteps', 10000000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -2,7 +2,7 @@
2
  - - - algo
3
  - dqn
4
  - - conf_file
5
- - /kaggle/input/config/pm_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
@@ -32,7 +32,7 @@
32
  - - n_startup_trials
33
  - 10
34
  - - n_timesteps
35
- - -1
36
  - - n_trials
37
  - 500
38
  - - no_optim_plots
@@ -50,11 +50,11 @@
50
  - - sampler
51
  - tpe
52
  - - save_freq
53
- - 1000
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 578119921
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
+ - null
6
  - - device
7
  - auto
8
  - - env
 
18
  - - hyperparams
19
  - null
20
  - - log_folder
21
+ - logs
22
  - - log_interval
23
  - -1
24
  - - max_total_trials
 
32
  - - n_startup_trials
33
  - 10
34
  - - n_timesteps
35
+ - 20000
36
  - - n_trials
37
  - 500
38
  - - no_optim_plots
 
50
  - - sampler
51
  - tpe
52
  - - save_freq
53
+ - 4000
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 647879404
58
  - - storage
59
  - null
60
  - - study_name
 
64
  - - track
65
  - false
66
  - - trained_agent
67
+ - /kaggle/working/logs/dqn/ALE-Pacman-v5_1/ALE-Pacman-v5.zip
68
  - - truncate_last_trajectory
69
  - true
70
  - - uuid
config.yml CHANGED
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 10000
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 10000000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
dqn-ALE-Pacman-v5.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:04e9ae5963ed1b75acc8b0057ec924b9a2a5ed5421a77d6928d7ec6445cdff00
3
- size 13710529
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e956ad9cec5fc385f3185a4e10d0a8ebfc6c3d994c03b61060e370cbdb27345
3
+ size 13710777
dqn-ALE-Pacman-v5/data CHANGED
The diff for this file is too large to render. See raw diff
 
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 1.0, "std_reward": 0.0, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-03-26T20:22:44.164461"}
 
1
+ {"mean_reward": 1.0, "std_reward": 0.0, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-03-26T20:31:56.883874"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:249c2a18e980fa51dd3190c5dadb6afebb8874c90aad59b5f9ea1da21378323f
3
- size 2036
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9fdf096b3c644fccae250b1ac369ee1087c6f9d1dcb9bd84f87df9ba3785c7c
3
+ size 3901