Hugging Face's logo

Amird99
/
DQN_SpaceInvaders_v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results (legacy)
Model card Files
xet
Community
Amird99 commited on
Commit
1df2bf3
·
verified ·
1 Parent(s): 0a57e51

Initial commit

Browse files
Files changed (9) hide show
  1. README.md +2 -2
  2. args.yml +1 -1
  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. results.json +1 -1
  9. 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: 742.50 +/- 305.21
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -63,7 +63,7 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
63
 
64
  ## Hyperparameters
65
  ```python
66
- OrderedDict([('batch_size', 32),
67
  ('buffer_size', 100000),
68
  ('env_wrapper',
69
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 605.50 +/- 125.51
20
  name: mean_reward
21
  verified: false
22
  ---
 
63
 
64
  ## Hyperparameters
65
  ```python
66
+ OrderedDict([('batch_size', 64),
67
  ('buffer_size', 100000),
68
  ('env_wrapper',
69
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
args.yml CHANGED
@@ -56,7 +56,7 @@
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
- - 3745347019
60
  - - storage
61
  - null
62
  - - study_name
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 4236190524
60
  - - storage
61
  - null
62
  - - study_name
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:da840b78f281c3c71b9756131a838bf85c12e99098302d7b5fd155ae28bccdda
3
- size 27218412
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79a463c184a06f95ce892d86f47c6c28bc248bbf54999963b50d221da8a5a2c2
3
+ size 27218408
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:b4dfe96d55c7595e0f06eb1c1c810f429a43569cfc4dcf73f2a04e9b482311ad
3
  size 13506172
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b577826f6812c69c992e97a2fb85a712b1d55ed4b31244439877f5b1465eceda
3
  size 13506172
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:60ce88709abeb3745cefd4d8218aaaaf043c304332d9c3485bb2d463efc1e489
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca261109c7bfdd568b6314638ccfd37ac4350654a7b14d9deaa0cc7498593cbf
3
  size 13505370
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 742.5, "std_reward": 305.20689703871375, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-05-26T17:46:21.179413"}
 
1
+ {"mean_reward": 605.5, "std_reward": 125.50796787455369, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-05-26T18:59:53.831401"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:866b5c339aadc457d5888ae89a4ac0bdb609dcb5a2f12f24656fa5a4e5cecddf
3
- size 37084
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a234e3a81579451f749f15fc661c825daf3fa800eb3aff4f166cf94036e8263
3
+ size 35170