Hugging Face's logo

DTambu
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results (legacy)
Model card Files
xet
Community
DTambu commited on
Commit
248bf92
·
verified ·
1 Parent(s): 80cec9b

Initial commit

Browse files
Files changed (9) hide show
  1. README.md +4 -4
  2. args.yml +1 -1
  3. config.yml +3 -3
  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: 238.00 +/- 81.83
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -64,7 +64,7 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
64
  ## Hyperparameters
65
  ```python
66
  OrderedDict([('batch_size', 32),
67
- ('buffer_size', 100000),
68
  ('env_wrapper',
69
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
70
  ('exploration_final_eps', 0.01),
@@ -72,8 +72,8 @@ OrderedDict([('batch_size', 32),
72
  ('frame_stack', 4),
73
  ('gradient_steps', 1),
74
  ('learning_rate', 0.0001),
75
- ('learning_starts', 100000),
76
- ('n_timesteps', 1000000.0),
77
  ('optimize_memory_usage', False),
78
  ('policy', 'CnnPolicy'),
79
  ('target_update_interval', 1000),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 496.50 +/- 124.12
20
  name: mean_reward
21
  verified: false
22
  ---
 
64
  ## Hyperparameters
65
  ```python
66
  OrderedDict([('batch_size', 32),
67
+ ('buffer_size', 120000),
68
  ('env_wrapper',
69
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
70
  ('exploration_final_eps', 0.01),
 
72
  ('frame_stack', 4),
73
  ('gradient_steps', 1),
74
  ('learning_rate', 0.0001),
75
+ ('learning_starts', 120000),
76
+ ('n_timesteps', 1500000.0),
77
  ('optimize_memory_usage', False),
78
  ('policy', 'CnnPolicy'),
79
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -56,7 +56,7 @@
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
- - 1901817032
60
  - - storage
61
  - null
62
  - - study_name
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 2169735394
60
  - - storage
61
  - null
62
  - - study_name
config.yml CHANGED
@@ -2,7 +2,7 @@
2
  - - - batch_size
3
  - 32
4
  - - buffer_size
5
- - 100000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
@@ -16,9 +16,9 @@
16
  - - learning_rate
17
  - 0.0001
18
  - - learning_starts
19
- - 100000
20
  - - n_timesteps
21
- - 1000000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
2
  - - - batch_size
3
  - 32
4
  - - buffer_size
5
+ - 120000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
 
16
  - - learning_rate
17
  - 0.0001
18
  - - learning_starts
19
+ - 120000
20
  - - n_timesteps
21
+ - 1500000.0
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 sha256:4d32900cdd341a6bc005bc94f6caacfc821c423a8e0e49dc8705c98f0422bde6
3
- size 27221650
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64af4b6f812d101891ec97c6903c5ab81b2c6cd674c44ee428934687d26590c8
3
+ size 27221651
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 sha256:03b6f27fd2e5c33c0fdbf88caa2703d91468806ba5e968ca51d4b4a5d1e56d0e
3
  size 13506172
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c03726c05618d96a00365d00d9656bae7bb854283f09fc8db153c33196553802
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:fa2a54eba87aeebd0c100b8bdd2a261cc79c8c6a3158dbb7c3a1c3541f005f92
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b068969b1ba6c357c5852aefc26599e77db5cfad8ce2e13a7544a1b16dee43f
3
  size 13505370
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 238.0, "std_reward": 81.82909018191513, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-04-21T01:24:59.047896"}
 
1
+ {"mean_reward": 496.5, "std_reward": 124.11788751022151, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-04-21T22:17:18.330484"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:74ae544058e20c1d5ae4e8c21115e245e4a6c7cd16949cd2ce4c06f003a76bb6
3
- size 41603
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10ef9eb054bcf2d2bda9214ffed9d2d9996f13036d64618b8946615fca49b7c9
3
+ size 61091