Hugging Face's logo

sayby
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
sayby commited on
Commit
47583f8
•
1 Parent(s): 98bc975

Initial commit

Browse files
Files changed (10) hide show
  1. README.md +3 -3
  2. args.yml +1 -1
  3. config.yml +2 -2
  4. dqn-SpaceInvadersNoFrameskip-v4.zip +2 -2
  5. dqn-SpaceInvadersNoFrameskip-v4/data +0 -0
  6. dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth +2 -2
  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: 15.50 +/- 12.54
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -58,7 +58,7 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
58
  ## Hyperparameters
59
  ```python
60
  OrderedDict([('batch_size', 32),
61
- ('buffer_size', 10000),
62
  ('env_wrapper',
63
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
64
  ('exploration_final_eps', 0.01),
@@ -67,7 +67,7 @@ OrderedDict([('batch_size', 32),
67
  ('gradient_steps', 1),
68
  ('learning_rate', 0.0001),
69
  ('learning_starts', 100000),
70
- ('n_timesteps', 100000.0),
71
  ('optimize_memory_usage', False),
72
  ('policy', 'CnnPolicy'),
73
  ('target_update_interval', 1000),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 653.50 +/- 137.33
20
  name: mean_reward
21
  verified: false
22
  ---
 
58
  ## Hyperparameters
59
  ```python
60
  OrderedDict([('batch_size', 32),
61
+ ('buffer_size', 100000),
62
  ('env_wrapper',
63
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
64
  ('exploration_final_eps', 0.01),
 
67
  ('gradient_steps', 1),
68
  ('learning_rate', 0.0001),
69
  ('learning_starts', 100000),
70
+ ('n_timesteps', 1000000.0),
71
  ('optimize_memory_usage', False),
72
  ('policy', 'CnnPolicy'),
73
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 1126139764
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 1620477641
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -2,7 +2,7 @@
2
  - - - batch_size
3
  - 32
4
  - - buffer_size
5
- - 10000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 100000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
2
  - - - batch_size
3
  - 32
4
  - - buffer_size
5
+ - 100000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 1000000.0
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:a457ce010a762244fa7608aa9eeb3d5076a42920b755962b5a56f64486cfdd58
3
- size 13720249
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:724f9bc3249d97136f99f6f913ef7b2b07c06370e752da822e9eb582372d7441
3
+ size 27225310
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:f1e067afe9912f3dd1b7925918b8cbe439229f6008e572c9c7e431ae731419f1
3
- size 687
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d1eb38ea972db73b2cc362349fd5d50e2e719dcd7f651f6f1ae939361e4a0f9
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:acd37d66e80ebe23b0b04323ea66e5984d20fbad54b54744076fe528789259c5
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3de2b132220f41a3cfbd1ec9bb3d6a51241ceed87baaf753b884651ae30721ac
3
  size 13504937
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:559d38137a7b613af28137d3d0ba83ac30ce3e6bdd65a44d7b0e42c6b77104d0
3
- size 272913
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:749da56147233090b30767a8ee609e65cf460de8eec5607272f7142f88861e82
3
+ size 245754
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 15.5, "std_reward": 12.539936203984453, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-01T15:34:06.875979"}
 
1
+ {"mean_reward": 653.5, "std_reward": 137.3326254027061, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-01T21:45:12.571662"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f0a83ae57a0a8375c70ff1e6096635a92e5f026a061d8af1b2cf5de745eb8d9e
3
- size 5646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7c49566a29fb59e604916e1a6cc6e4395cb5984d7c9efe2870a1b19479450ee
3
+ size 36889