Hugging Face's logo

ItchyB
/
rl_course_vizdoom_health_gathering_supreme

Reinforcement Learning
sample-factory
TensorBoard
deep-reinforcement-learning
Eval Results
Model card Files Metrics Community
ItchyB commited on
Commit
4e2de75
•
1 Parent(s): 10887b4

Upload folder using huggingface_hub

Browse files
Files changed (11) hide show
  1. .summary/0/events.out.tfevents.1682872521.CAPTAIN-AMERICA +3 -0
  2. .summary/0/events.out.tfevents.1682872522.CAPTAIN-AMERICA +3 -0
  3. .summary/0/events.out.tfevents.1682873036.CAPTAIN-AMERICA +3 -0
  4. .summary/0/events.out.tfevents.1682873133.CAPTAIN-AMERICA +3 -0
  5. README.md +1 -1
  6. checkpoint_p0/best_000000952_3899392_reward_20.801.pth +3 -0
  7. checkpoint_p0/checkpoint_000000967_3960832.pth +3 -0
  8. checkpoint_p0/checkpoint_000000979_4009984.pth +3 -0
  9. config.json +10 -7
  10. replay.mp4 +2 -2
  11. sf_log.txt +0 -0
.summary/0/events.out.tfevents.1682872521.CAPTAIN-AMERICA ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e8350011c63a7ca74e2c680f5eb65121a5f9b5a224f6f3c2a07908ad31faf87
3
+ size 40
.summary/0/events.out.tfevents.1682872522.CAPTAIN-AMERICA ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e2ea52e528a8a7f90a425fd33f0af2d3df1065218c040d40e9b500db81e877c
3
+ size 40
.summary/0/events.out.tfevents.1682873036.CAPTAIN-AMERICA ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47e2122200a33c3ea964933b85480bdcbd847455264daaa3fc1bd4154129ab51
3
+ size 4533
.summary/0/events.out.tfevents.1682873133.CAPTAIN-AMERICA ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:052ad19b2708a0ea7c4c39d623c3e5ac81e7c4069f30c28d1a56deed73399770
3
+ size 817056
README.md CHANGED
@@ -15,7 +15,7 @@ model-index:
15
  type: doom_health_gathering_supreme
16
  metrics:
17
  - type: mean_reward
18
- value: 4.10 +/- 0.49
19
  name: mean_reward
20
  verified: false
21
  ---
 
15
  type: doom_health_gathering_supreme
16
  metrics:
17
  - type: mean_reward
18
+ value: 10.34 +/- 4.12
19
  name: mean_reward
20
  verified: false
21
  ---
checkpoint_p0/best_000000952_3899392_reward_20.801.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36ad9decdfc0ebe31465a4fea8bd853c2bcbfaf63375c2369115351dae90b95a
3
+ size 34928419
checkpoint_p0/checkpoint_000000967_3960832.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e453665eac0bdd0dd79d79b3bb8450f1e9a7e8eb2e91988b123d48fd28d52c5
3
+ size 34928851
checkpoint_p0/checkpoint_000000979_4009984.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3271a34eaa6a0a5e988c56335786d4eafdd81d44f2940dde7c5fef29c9163c8b
3
+ size 34928851
config.json CHANGED
@@ -2,10 +2,10 @@
2
  "help": false,
3
  "algo": "APPO",
4
  "env": "doom_health_gathering_supreme",
5
- "experiment": "default_experiment",
6
- "train_dir": "/home/byron/projects/rl-learning-course/unit-08/train_dir",
7
  "restart_behavior": "resume",
8
- "device": "gpu",
9
  "seed": null,
10
  "num_policies": 1,
11
  "async_rl": true,
@@ -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,
@@ -130,12 +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": "unknown",
141
  "git_repo_name": "not a git repository"
 
2
  "help": false,
3
  "algo": "APPO",
4
  "env": "doom_health_gathering_supreme",
5
+ "experiment": "doom_health_gathering_supreme",
6
+ "train_dir": "./train_dir",
7
  "restart_behavior": "resume",
8
+ "device": "cpu",
9
  "seed": null,
10
  "num_policies": 1,
11
  "async_rl": true,
 
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,
 
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=8 --train_for_env_steps=10000 --experiment=doom_health_gathering_supreme --train_dir=./train_dir --device=cpu",
134
  "cli_args": {
135
  "env": "doom_health_gathering_supreme",
136
+ "experiment": "doom_health_gathering_supreme",
137
+ "train_dir": "./train_dir",
138
+ "device": "cpu",
139
  "num_workers": 8,
140
+ "num_envs_per_worker": 8,
141
+ "train_for_env_steps": 10000
142
  },
143
  "git_hash": "unknown",
144
  "git_repo_name": "not a git repository"
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d032c87a2efab0e06ac7ac1ce54c8ae2332a4fa365b19ca4bd69561d097bdd8b
3
- size 6150210
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e5576f5e772fb4441f2ec9cd91b6ac73d1fc3df2228b2d332d15fe194d3d553
3
+ size 19722469
sf_log.txt CHANGED
The diff for this file is too large to render. See raw diff