Hugging Face's logo

AgentXXX
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
AgentXXX commited on
Commit
5720bae
•
1 Parent(s): 549b6ac

Initial commit

Browse files
Files changed (12) 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/_stable_baselines3_version +1 -1
  6. dqn-SpaceInvadersNoFrameskip-v4/data +0 -0
  7. dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth +2 -2
  8. dqn-SpaceInvadersNoFrameskip-v4/policy.pth +2 -2
  9. dqn-SpaceInvadersNoFrameskip-v4/system_info.txt +2 -2
  10. replay.mp4 +2 -2
  11. results.json +1 -1
  12. 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: 519.50 +/- 102.46
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -67,7 +67,7 @@ OrderedDict([('batch_size', 32),
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),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 752.00 +/- 227.35
20
  name: mean_reward
21
  verified: false
22
  ---
 
67
  ('gradient_steps', 1),
68
  ('learning_rate', 0.0001),
69
  ('learning_starts', 100000),
70
+ ('n_timesteps', 3000000.0),
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
- - 2046143677
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 3622858413
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 1000000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 3000000.0
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 sha256:86c2003c0ed23a62df5dc3dd874c7df738ac8a9c2b042101c5f8a1ebbca13ace
3
- size 27224788
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a96b7be5838afbe5cf3b3f082eb9e35ec1f0434efd493fdb49feeec589e330c
3
+ size 27224299
dqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version CHANGED
@@ -1 +1 @@
1
- 1.6.2
 
1
+ 1.7.0a10
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:b113f86e6ed20005c7371b94b84e526c935b588028aae05c6b2f95b75798a9c4
3
- size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c25d2bbc86eda3d3016beb0211bc35b0aa4c441adf011ddf70151f46a29957c5
3
+ size 13505419
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52faba05a4b90009c2151ce8ff1cc5e61c9fc2eb977ec68c5306b94408a58dec
3
- size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b6bf4889444069a79e4e4f683a289675f1be5597bd2720a74db6f8f32a1cb59
3
+ size 13504745
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -1,7 +1,7 @@
1
  OS: Linux-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022
2
  Python: 3.8.16
3
- Stable-Baselines3: 1.6.2
4
  PyTorch: 1.13.0+cu116
5
- GPU Enabled: True
6
  Numpy: 1.21.6
7
  Gym: 0.21.0
 
1
  OS: Linux-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022
2
  Python: 3.8.16
3
+ Stable-Baselines3: 1.7.0a10
4
  PyTorch: 1.13.0+cu116
5
+ GPU Enabled: False
6
  Numpy: 1.21.6
7
  Gym: 0.21.0
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d171c7d8c236962deacdcf3a4ea4b11bd57ade5cad702d73fda6744360872c8c
3
- size 225663
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e96ce9455a0a6607851db3e4e4a6b804684cb7fe66ce8ed1810bbc7e700d0149
3
+ size 205226
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 519.5, "std_reward": 102.45608815487735, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-19T20:27:11.241631"}
 
1
+ {"mean_reward": 752.0, "std_reward": 227.34555196880365, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-23T13:27:15.812952"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4435700483fbf0339fad0490a1a9c72cd15cdddb506c24190cc569527eea4027
3
- size 36251
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c814ea1fe9708fcc36eb2358160252f2a6e1cb4d4cd36abaa45a7619f038ff1
3
+ size 74469