Hugging Face's logo

Alex48
/
SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results (legacy)
Model card Files
xet
Community
Alex48 commited on
Commit
cd05114
·
1 Parent(s): 85f224e

Initial commit

Browse files
Files changed (10) hide show
  1. README.md +2 -2
  2. args.yml +6 -4
  3. config.yml +1 -1
  4. dqn-SpaceInvadersNoFrameskip-v4.zip +2 -2
  5. dqn-SpaceInvadersNoFrameskip-v4/data +0 -0
  6. dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth +1 -1
  7. dqn-SpaceInvadersNoFrameskip-v4/policy.pth +1 -1
  8. replay.mp4 +2 -2
  9. results.json +1 -1
  10. train_eval_metrics.zip +2 -2
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
- value: 794.00 +/- 247.23
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -62,7 +62,7 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
62
 
63
  ## Hyperparameters
64
  ```python
65
- OrderedDict([('batch_size', 32),
66
  ('buffer_size', 100000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 429.00 +/- 104.83
20
  name: mean_reward
21
  verified: false
22
  ---
 
62
 
63
  ## Hyperparameters
64
  ```python
65
+ OrderedDict([('batch_size', 64),
66
  ('buffer_size', 100000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
args.yml CHANGED
@@ -1,6 +1,8 @@
1
  !!python/object/apply:collections.OrderedDict
2
  - - - algo
3
  - dqn
 
 
4
  - - conf_file
5
  - null
6
  - - device
@@ -32,7 +34,7 @@
32
  - - n_startup_trials
33
  - 10
34
  - - n_timesteps
35
- - 1000000
36
  - - n_trials
37
  - 500
38
  - - no_optim_plots
@@ -50,11 +52,11 @@
50
  - - sampler
51
  - tpe
52
  - - save_freq
53
- - 100000
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 3242211519
58
  - - storage
59
  - null
60
  - - study_name
@@ -64,7 +66,7 @@
64
  - - track
65
  - false
66
  - - trained_agent
67
- - ''
68
  - - truncate_last_trajectory
69
  - true
70
  - - uuid
 
1
  !!python/object/apply:collections.OrderedDict
2
  - - - algo
3
  - dqn
4
+ - - batch_size
5
+ - 64
6
  - - conf_file
7
  - null
8
  - - device
 
34
  - - n_startup_trials
35
  - 10
36
  - - n_timesteps
37
+ - 300000
38
  - - n_trials
39
  - 500
40
  - - no_optim_plots
 
52
  - - sampler
53
  - tpe
54
  - - save_freq
55
+ - -1
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 1077805044
60
  - - storage
61
  - null
62
  - - study_name
 
66
  - - track
67
  - false
68
  - - trained_agent
69
+ - logs/dqn/SpaceInvadersNoFrameskip-v4_10/SpaceInvadersNoFrameskip-v4.zip
70
  - - truncate_last_trajectory
71
  - true
72
  - - uuid
config.yml CHANGED
@@ -1,6 +1,6 @@
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
- - 32
4
  - - buffer_size
5
  - 100000
6
  - - env_wrapper
 
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
+ - 64
4
  - - buffer_size
5
  - 100000
6
  - - env_wrapper
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6526c75d2aab149fb8a33789a536b59ff21d3335df7535760934e0c159021175
3
- size 27224807
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e712831c135c3f9c22b3dc0d2d94ee21a38e11ddb3d10ece243c508fa22b6910
3
+ size 27224805
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 sha256:7a6edc7dc842a574379bede3a7fb4d41843b86641b9248d95b19cf959cc92aa0
3
  size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d822b3ad500287b5ce58332b15deb30f3922a50f8f5b5180335fdee9604ae988
3
  size 13505739
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5884d000da089a1d98d2f9284741a6ac57d52037035966483b1dc0f7ebebbc61
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0aabe568624c61b4750c82060f17d8d27bea5ec09e911519f8ff0c7a88fb9978
3
  size 13504937
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e41ea531f1520c05a66684eec10c00f10517eb05cfa19ef4beda5810799ae6e
3
- size 239758
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5980b19cd191317e461d9baf5f499b6a0eeebe915ee1d355d005007776081017
3
+ size 234977
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 794.0, "std_reward": 247.2326839234651, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-02-20T23:46:14.319918"}
 
1
+ {"mean_reward": 429.0, "std_reward": 104.82843125793688, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-02-21T01:28:43.262798"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:14d915c56248fdebdce8c0310d15a3aa0f7c7ba9cfecb6f43cb35f65efbb59a9
3
- size 37873
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30c75a8eb7763a9dc26c24494e3546ea4d8534eb93cc92344b5440e802aa8c30
3
+ size 11151