Hugging Face's logo

monti-python
/
rl_course_vizdoom_health_gathering_supreme

Reinforcement Learning
sample-factory
TensorBoard
deep-reinforcement-learning
Eval Results
Model card Files Metrics Community
monti-python commited on
Commit
574e16f
•
1 Parent(s): beabd9a

Upload folder using huggingface_hub

Browse files
Files changed (13) hide show
  1. .summary/0/events.out.tfevents.1727633083.4b93c3da0fb6 +3 -0
  2. .summary/0/events.out.tfevents.1727633208.4b93c3da0fb6 +3 -0
  3. .summary/0/events.out.tfevents.1727633577.4b93c3da0fb6 +3 -0
  4. .summary/0/events.out.tfevents.1727634478.4b93c3da0fb6 +3 -0
  5. .summary/0/events.out.tfevents.1727635182.4b93c3da0fb6 +3 -0
  6. .summary/0/events.out.tfevents.1727636372.4b93c3da0fb6 +3 -0
  7. README.md +1 -1
  8. checkpoint_p0/best_000004515_18493440_reward_36.367.pth +3 -0
  9. checkpoint_p0/checkpoint_000004818_19734528.pth +3 -0
  10. checkpoint_p0/checkpoint_000004884_20004864.pth +3 -0
  11. config.json +9 -7
  12. replay.mp4 +2 -2
  13. sf_log.txt +0 -0
.summary/0/events.out.tfevents.1727633083.4b93c3da0fb6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc5ad5bbfd0441ae3992e1b77ae4797fd9178675cbc207b60a355d6b3d561477
3
+ size 4959
.summary/0/events.out.tfevents.1727633208.4b93c3da0fb6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18f08d1ebf6cc9f1ad6c11cd621eb66fbd6bfb306013605ec160ed178aa68396
3
+ size 226103
.summary/0/events.out.tfevents.1727633577.4b93c3da0fb6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3844e5192a0f5180b45d5772aa3e1f77584a1cb811540428166003e41f537cee
3
+ size 678935
.summary/0/events.out.tfevents.1727634478.4b93c3da0fb6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06bf72cf05d4c90738ecb478fa08f18774d0d742f6bf52b0dae870bc5dd94848
3
+ size 396127
.summary/0/events.out.tfevents.1727635182.4b93c3da0fb6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79fb37526e706d99adb95123274126a73eb26060190b1f55c282d9d77d49b7d1
3
+ size 708457
.summary/0/events.out.tfevents.1727636372.4b93c3da0fb6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4440509004bf2170e7420285adc942d4a674516781c8a5053dc8e6d3d98b7e70
3
+ size 1547527
README.md CHANGED
@@ -15,7 +15,7 @@ model-index:
15
  type: doom_health_gathering_supreme
16
  metrics:
17
  - type: mean_reward
18
- value: 4.13 +/- 0.36
19
  name: mean_reward
20
  verified: false
21
  ---
 
15
  type: doom_health_gathering_supreme
16
  metrics:
17
  - type: mean_reward
18
+ value: 11.96 +/- 6.26
19
  name: mean_reward
20
  verified: false
21
  ---
checkpoint_p0/best_000004515_18493440_reward_36.367.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed11a4077a20ff43e10f7ef5097bd6203bad1d1887915b27fd3bc5cb6330bfa5
3
+ size 34928806
checkpoint_p0/checkpoint_000004818_19734528.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:271bb7b25da7230939733b63d62e51c34e05b5fc01d93de1231b7e0b1c090ee4
3
+ size 34929220
checkpoint_p0/checkpoint_000004884_20004864.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74cb5b923fe9a19694d8e16b5dcdf1d02a66b78fd513ed8c92a0d009c0cae3dc
3
+ size 34929220
config.json CHANGED
@@ -2,8 +2,8 @@
2
  "help": false,
3
  "algo": "APPO",
4
  "env": "doom_health_gathering_supreme",
5
- "experiment": "default_experiment",
6
- "train_dir": "/home/montana/repos/deep-rl/unit8-ppo/train_dir",
7
  "restart_behavior": "resume",
8
  "device": "gpu",
9
  "seed": null,
@@ -65,7 +65,7 @@
65
  "summaries_use_frameskip": true,
66
  "heartbeat_interval": 20,
67
  "heartbeat_reporting_interval": 600,
68
- "train_for_env_steps": 4000000,
69
  "train_for_seconds": 10000000000,
70
  "save_every_sec": 120,
71
  "keep_checkpoints": 2,
@@ -130,13 +130,15 @@
130
  "wide_aspect_ratio": false,
131
  "eval_env_frameskip": 1,
132
  "fps": 35,
133
- "command_line": "--env=doom_health_gathering_supreme --num_workers=8 --num_envs_per_worker=4 --train_for_env_steps=4000000",
134
  "cli_args": {
135
  "env": "doom_health_gathering_supreme",
 
 
136
  "num_workers": 8,
137
  "num_envs_per_worker": 4,
138
- "train_for_env_steps": 4000000
139
  },
140
- "git_hash": "e923ca6811d177eb3a7a4b268a75d06335cade44",
141
- "git_repo_name": "https://github.com/monti-python/deep-rl.git"
142
  }
 
2
  "help": false,
3
  "algo": "APPO",
4
  "env": "doom_health_gathering_supreme",
5
+ "experiment": "samplefactory-vizdoom-v1",
6
+ "train_dir": "/content/train_dir",
7
  "restart_behavior": "resume",
8
  "device": "gpu",
9
  "seed": null,
 
65
  "summaries_use_frameskip": true,
66
  "heartbeat_interval": 20,
67
  "heartbeat_reporting_interval": 600,
68
+ "train_for_env_steps": 20000000,
69
  "train_for_seconds": 10000000000,
70
  "save_every_sec": 120,
71
  "keep_checkpoints": 2,
 
130
  "wide_aspect_ratio": false,
131
  "eval_env_frameskip": 1,
132
  "fps": 35,
133
+ "command_line": "--env=doom_health_gathering_supreme --num_workers=8 --num_envs_per_worker=4 --train_for_env_steps=10000 --experiment=samplefactory-vizdoom-v1 --restart_behavior=resume",
134
  "cli_args": {
135
  "env": "doom_health_gathering_supreme",
136
+ "experiment": "samplefactory-vizdoom-v1",
137
+ "restart_behavior": "resume",
138
  "num_workers": 8,
139
  "num_envs_per_worker": 4,
140
+ "train_for_env_steps": 10000
141
  },
142
+ "git_hash": "unknown",
143
+ "git_repo_name": "not a git repository"
144
  }
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a512e52cbba0bf31bfa9d46368b8cc8a8632e1557a8202f8d2e720e310cedcb2
3
- size 6488396
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9d23ac390ccd4490b89d7dacafb9dcf4f663505cc557c790330c3de11ff80ce
3
+ size 23228470
sf_log.txt CHANGED
The diff for this file is too large to render. See raw diff