Hugging Face's logo

NorbertRop
/
qrdqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
NorbertRop commited on
Commit
f67cce7
•
1 Parent(s): 72c6527

Initial commit

Browse files
Files changed (10) hide show
  1. README.md +4 -4
  2. args.yml +3 -3
  3. config.yml +4 -4
  4. qrdqn-SpaceInvadersNoFrameskip-v4.zip +1 -1
  5. qrdqn-SpaceInvadersNoFrameskip-v4/data +0 -0
  6. qrdqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth +1 -1
  7. qrdqn-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: 2380.00 +/- 1021.83
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -57,13 +57,13 @@ python -m rl_zoo3.push_to_hub --algo qrdqn --env SpaceInvadersNoFrameskip-v4 -f
57
 
58
  ## Hyperparameters
59
  ```python
60
- OrderedDict([('env_wrapper',
 
61
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
62
  ('exploration_fraction', 0.025),
63
  ('frame_stack', 4),
64
  ('n_timesteps', 10000000.0),
65
- ('optimize_memory_usage', True),
66
  ('policy', 'CnnPolicy'),
67
- ('replay_buffer_kwargs', {'handle_timeout_termination': False}),
68
  ('normalize', False)])
69
  ```
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 6264.00 +/- 3562.06
20
  name: mean_reward
21
  verified: false
22
  ---
 
57
 
58
  ## Hyperparameters
59
  ```python
60
+ OrderedDict([('batch_size', 64),
61
+ ('env_wrapper',
62
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
63
  ('exploration_fraction', 0.025),
64
  ('frame_stack', 4),
65
  ('n_timesteps', 10000000.0),
66
+ ('optimize_memory_usage', False),
67
  ('policy', 'CnnPolicy'),
 
68
  ('normalize', False)])
69
  ```
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
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 2278474354
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
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 222532327
58
  - - storage
59
  - null
60
  - - study_name
 
64
  - - track
65
  - false
66
  - - trained_agent
67
+ - ./logs/qrdqn/SpaceInvadersNoFrameskip-v4_1/SpaceInvadersNoFrameskip-v4.zip
68
  - - truncate_last_trajectory
69
  - true
70
  - - uuid
config.yml CHANGED
@@ -1,5 +1,7 @@
1
  !!python/object/apply:collections.OrderedDict
2
- - - - env_wrapper
 
 
3
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
4
  - - exploration_fraction
5
  - 0.025
@@ -8,8 +10,6 @@
8
  - - n_timesteps
9
  - 10000000.0
10
  - - optimize_memory_usage
11
- - true
12
  - - policy
13
  - CnnPolicy
14
- - - replay_buffer_kwargs
15
- - handle_timeout_termination: false
 
1
  !!python/object/apply:collections.OrderedDict
2
+ - - - batch_size
3
+ - 64
4
+ - - env_wrapper
5
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
6
  - - exploration_fraction
7
  - 0.025
 
10
  - - n_timesteps
11
  - 10000000.0
12
  - - optimize_memory_usage
13
+ - false
14
  - - policy
15
  - CnnPolicy
 
 
qrdqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:421cdc4e664450b2b26eea3d1b1b0e5f15760d702cf642ce2bd56a97479488a3
3
  size 37025441
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecb30def4139c40d64fc7af126b1fa2b078fc46e5f2bb60bcd86901eb2dbee9a
3
  size 37025441
qrdqn-SpaceInvadersNoFrameskip-v4/data CHANGED
The diff for this file is too large to render. See raw diff
 
qrdqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4d4a5d70fb13d574d70b127c45a28244470b9ad0171853ab2aefa5e445a6f2b8
3
  size 18405963
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:688aadbabffcfa22ad4b8aa5d73baacebd75bf6c5341ee9beba43fb9fb30b680
3
  size 18405963
qrdqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b19d90be5f922d73855840e1610918ddd842e81c12b53b19b925ff98cc02e2ea
3
  size 18405545
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da866154b2a4ab9955a907216a7a69328b500cb363395fd9cb4f775647499f4a
3
  size 18405545
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d946231620f424d684eddbf28d9cc3412f28957e9a6d696e1e82fa8cb568d90a
3
- size 188153
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aaeb9a115c7238a0031418ec1874ac8bcd5b29c40212526d03cdd7fa2e084d57
3
+ size 201840
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 2380.0, "std_reward": 1021.8316886845896, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-25T21:30:20.561722"}
 
1
+ {"mean_reward": 6264.0, "std_reward": 3562.0603588372837, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-26T10:47:31.247000"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e5ba2c3e23066d1536cc1ab5355f95559657db9ac4b78fc69c449d215b98103
3
- size 249606
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e3a11c694ab2e458c0536ae12b809fda60189c6378f07f9f7b5e734eba5e736
3
+ size 127941