Hugging Face's logo

zbenmo
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
zbenmo commited on
Commit
f11c117
·
1 Parent(s): bf60882

Initial commit

Browse files
Files changed (11) 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 +2 -2
  7. dqn-SpaceInvadersNoFrameskip-v4/policy.pth +2 -2
  8. dqn-SpaceInvadersNoFrameskip-v4/system_info.txt +5 -5
  9. replay.mp4 +2 -2
  10. results.json +1 -1
  11. 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: 646.50 +/- 170.29
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: 619.50 +/- 144.11
20
  name: mean_reward
21
  verified: false
22
  ---
 
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
- - 2189713705
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 273877323
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
+ - 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 sha256:77147a5fbcec7fa7628b60a3fc38a637bd82e6fa3d76790a8b0afd3e7e61e18d
3
- size 27224089
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6177daa6be721eb9ebcdf1b2f1f832905f59210f4ffb8950764dff66aa32397c
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 sha256:61f219f6c11f165e4f6c023129ed9183516f9af38e5134422fb1f16f0a86b8ce
3
- size 13505419
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f02211861967b7d5ac67eb04088bf3ce4bf615c5f456b6f80db15722e71cdbcf
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:f64eb4e487fb45043ece19f16843b3bc2c38f94cfecbc531362bcf807a8b7e53
3
- size 13504745
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ddb6c827fb5ba109c8a51ad04494f8e0f05ef41b486272032086dad96493ffa
3
+ size 13504937
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -1,7 +1,7 @@
1
- OS: Linux-4.19.128-microsoft-standard-x86_64-with-glibc2.29 #1 SMP Tue Jun 23 12:58:10 UTC 2020
2
- Python: 3.8.10
3
  Stable-Baselines3: 1.7.0a10
4
- PyTorch: 1.13.0+cu117
5
- GPU Enabled: False
6
- Numpy: 1.23.5
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: True
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 sha256:0ff626c3e084b89b845158c779a9af93d2362267b9c6b0dc08bbaf1b11c0bde8
3
- size 199184
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75f6b6a4f5b7f916b40fdef484e071eea8b653242affbe306b4ac6028edc87f3
3
+ size 208379
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 646.5, "std_reward": 170.29459768295646, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-25T13:11:38.338213"}
 
1
+ {"mean_reward": 619.5, "std_reward": 144.10846609411954, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-25T14:17:47.949756"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa590c2baa54b9f25137d60e743bb16b60b1c80ae58275e699edb05a0376219b
3
- size 37364
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:937d03493cd3e3af5699d1a5881c8b52274731dabd12b20b664e568a35d50f89
3
+ size 64835