Hugging Face's logo

patonw
/
rl_course_vizdoom_health_gathering_supreme

Reinforcement Learning
sample-factory
TensorBoard
deep-reinforcement-learning
Eval Results
Model card Files Metrics Community
patonw commited on
Commit
a38b86e
•
1 Parent(s): 79ee852

Upload folder using huggingface_hub

Browse files
Files changed (10) hide show
  1. .summary/0/events.out.tfevents.1692302948.muon +3 -0
  2. .summary/0/events.out.tfevents.1692303063.muon +3 -0
  3. README.md +1 -1
  4. checkpoint_p0/best_000023913_97947648_reward_50.917.pth +3 -0
  5. checkpoint_p0/checkpoint_000023651_96874496.pth +3 -0
  6. checkpoint_p0/checkpoint_000024416_100007936.pth +3 -0
  7. config.json +2 -2
  8. git.diff +2 -2
  9. replay.mp4 +2 -2
  10. sf_log.txt +0 -0
.summary/0/events.out.tfevents.1692302948.muon ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0dfb8801f0215f962b4f0e8dbe564ac0d5a7cc225810b74b1c6f4fb6778ab8e
3
+ size 58945
.summary/0/events.out.tfevents.1692303063.muon ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f05309047eb11e4d16b4c35a035d6bcad260ac6876553e246538dad33a37d601
3
+ size 595131
README.md CHANGED
@@ -15,7 +15,7 @@ model-index:
15
  type: doom_health_gathering_supreme
16
  metrics:
17
  - type: mean_reward
18
- value: 11.85 +/- 5.93
19
  name: mean_reward
20
  verified: false
21
  ---
 
15
  type: doom_health_gathering_supreme
16
  metrics:
17
  - type: mean_reward
18
+ value: 18.12 +/- 4.10
19
  name: mean_reward
20
  verified: false
21
  ---
checkpoint_p0/best_000023913_97947648_reward_50.917.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e61d50ec191dfd5220930713fcac0bb7cd5dc1cfa2dac3b3586f91dfbb51044
3
+ size 34928806
checkpoint_p0/checkpoint_000023651_96874496.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c319372b846df448733aa7c22e3f59878481848e513993ec9b3e1af000d47b0
3
+ size 34929220
checkpoint_p0/checkpoint_000024416_100007936.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b43b4c97516a1bffd686ac5ec6cdbfd7e22219483964da0792fd9867809826a
3
+ size 34929220
config.json CHANGED
@@ -16,7 +16,7 @@
16
  "policy_workers_per_policy": 1,
17
  "max_policy_lag": 1000,
18
  "num_workers": 8,
19
- "num_envs_per_worker": 4,
20
  "batch_size": 1024,
21
  "num_batches_per_epoch": 1,
22
  "num_epochs": 1,
@@ -65,7 +65,7 @@
65
  "summaries_use_frameskip": true,
66
  "heartbeat_interval": 20,
67
  "heartbeat_reporting_interval": 600,
68
- "train_for_env_steps": 10000000,
69
  "train_for_seconds": 10000000000,
70
  "save_every_sec": 120,
71
  "keep_checkpoints": 2,
 
16
  "policy_workers_per_policy": 1,
17
  "max_policy_lag": 1000,
18
  "num_workers": 8,
19
+ "num_envs_per_worker": 8,
20
  "batch_size": 1024,
21
  "num_batches_per_epoch": 1,
22
  "num_epochs": 1,
 
65
  "summaries_use_frameskip": true,
66
  "heartbeat_interval": 20,
67
  "heartbeat_reporting_interval": 600,
68
+ "train_for_env_steps": 100000000,
69
  "train_for_seconds": 10000000000,
70
  "save_every_sec": 120,
71
  "keep_checkpoints": 2,
git.diff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b13eae92b639415ce9ba9a749221da18413b278e037e3ccbb2ecb53ab698bdc7
3
- size 19093250
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:739a00808bb776e08a0114124865d7f106c89ec8f4d7ad357f0ed0bb84304f50
3
+ size 21696427
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd325b3be486b1cb6eae1418969fe4bbc491b0fdd15d9b76f669502007eaa328
3
- size 22633936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7055aacba1367ade5f3955bedc5d25aed4a60cb5cc451b5b5c93b88e6b90ba47
3
+ size 35756330
sf_log.txt CHANGED
The diff for this file is too large to render. See raw diff