Hugging Face's logo

CoreyMorris
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files
xet
Community
CoreyMorris commited on
Commit
b30eea3
·
1 Parent(s): f3522fa

Initial commit

Browse files
Files changed (10) hide show
  1. README.md +1 -1
  2. args.yml +4 -4
  3. config.yml +1 -1
  4. dqn-SpaceInvadersNoFrameskip-v4.zip +2 -2
  5. dqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version +1 -1
  6. dqn-SpaceInvadersNoFrameskip-v4/data +0 -0
  7. dqn-SpaceInvadersNoFrameskip-v4/policy.pth +1 -1
  8. dqn-SpaceInvadersNoFrameskip-v4/system_info.txt +1 -1
  9. results.json +1 -1
  10. train_eval_metrics.zip +2 -2
README.md CHANGED
@@ -67,7 +67,7 @@ OrderedDict([('batch_size', 32),
67
  ('gradient_steps', 1),
68
  ('learning_rate', 0.0001),
69
  ('learning_starts', 100000),
70
- ('n_timesteps', 200000.0),
71
  ('optimize_memory_usage', False),
72
  ('policy', 'CnnPolicy'),
73
  ('target_update_interval', 1000),
 
67
  ('gradient_steps', 1),
68
  ('learning_rate', 0.0001),
69
  ('learning_starts', 100000),
70
+ ('n_timesteps', 10000000.0),
71
  ('optimize_memory_usage', False),
72
  ('policy', 'CnnPolicy'),
73
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -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
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 3537882224
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
 
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
+ - 100000
36
  - - n_trials
37
  - 500
38
  - - no_optim_plots
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 947504359
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
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 200000.0
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-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cbbaf56747376c41b4455ab036930a0acef6aa1179bb1106c39e15e069e17821
3
- size 27224784
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9dc99717a4a30ea6dc04a346f8204e27a4e03c6f5d3fc619b6b3d811c094814
3
+ size 27224789
dqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version CHANGED
@@ -1 +1 @@
1
- 1.6.2
 
1
+ 1.7.0a10
dqn-SpaceInvadersNoFrameskip-v4/data CHANGED
The diff for this file is too large to render. See raw diff
 
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb40c10203d6588ed3718f95cb17d1eed948db1933dde254b22611513b4971df
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5800b3239d423dc6ff3cdfc0827664d09bd3b58d9b2472ff2be263a4ff084650
3
  size 13504937
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -1,6 +1,6 @@
1
  OS: Linux-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022
2
  Python: 3.8.16
3
- Stable-Baselines3: 1.6.2
4
  PyTorch: 1.13.0+cu116
5
  GPU Enabled: True
6
  Numpy: 1.21.6
 
1
  OS: Linux-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022
2
  Python: 3.8.16
3
+ Stable-Baselines3: 1.7.0a10
4
  PyTorch: 1.13.0+cu116
5
  GPU Enabled: True
6
  Numpy: 1.21.6
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 271.0, "std_reward": 44.14748010928823, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-22T20:45:56.707396"}
 
1
+ {"mean_reward": 271.0, "std_reward": 44.14748010928823, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-23T20:43:16.159004"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2dc281e010dd353af30910f8abd86df442c4c1a2f9b96ca2bfd8c076eb762b94
3
- size 10072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:198f5a1a5bdc39fe11d561af9b6c89805802af0cb8db33d8555cc8c346a6cb53
3
+ size 5942