Hugging Face's logo

Iamvincent
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
Iamvincent commited on
Commit
54f94be
·
1 Parent(s): 4b5e4be

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 +1 -1
  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: 585.00 +/- 135.15
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', 100000),
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', 1500000.0),
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: 799.00 +/- 199.62
20
  name: mean_reward
21
  verified: false
22
  ---
 
58
  ## Hyperparameters
59
  ```python
60
  OrderedDict([('batch_size', 32),
61
+ ('buffer_size', 200000),
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', 2000000.0),
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
- - 4215369725
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 3680328933
58
  - - storage
59
  - null
60
  - - 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
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 1500000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
2
  - - - batch_size
3
  - 32
4
  - - buffer_size
5
+ - 200000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 2000000.0
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 sha256:45f9cdcb9ec154d22d18bfaf7c8b4828ebdac37db3760eb5dffc9ff014ac156e
3
  size 27224794
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:516c7ea0bf00e2ba730bf2bba0d16d4e73af63d3e9f5078b26715cea3049a190
3
  size 27224794
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:c59954b48b3c3385ba314680d3c370fef9b7b01743bfa49bcae646274260b4ab
3
  size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e0bad37936a20c850adb660e8386bac244a4130fbb16a5cb0ea6b29880eeda4
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:d7754cf2dc9f01e90f3bb3985ef82341282bbb05cbdbb28e7fdb844cd7125572
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53b5ab2316bcb354887e3de8e0ecf2a61d99c02a342de89e9b97ae851001c6c8
3
  size 13504937
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b13515624283b32c93b4c502243d261bdd34e4eaf3deb7faafb34306fd16153c
3
- size 217007
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5ecceef1fb27f3d1616562ce53fe553670b3b9aca5126d6089946f501a0d005
3
+ size 216421
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 585.0, "std_reward": 135.14806694880988, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-27T14:16:37.505291"}
 
1
+ {"mean_reward": 799.0, "std_reward": 199.62214306033286, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-27T17:33:30.168249"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5885d25819afddfd9b1ef21f0905874da18ab67129104cbda064e26c7753d25e
3
- size 49870
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17516bed46a40b2683912a99300dc908e55ef03169c1247174f3324097bc3355
3
+ size 60331