elliemci commited on
Commit
d86b755
·
verified ·
1 Parent(s): a8afe22

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -8
README.md CHANGED
@@ -20,10 +20,9 @@ model-index:
20
  verified: false
21
  ---
22
 
23
- A(n) **APPO** model trained on the **doom_deadly_corridor** environment.
24
 
25
- This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory.
26
- Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
27
 
28
 
29
  ## Downloading the model
@@ -40,10 +39,6 @@ To run the model after download, use the `enjoy` script corresponding to this en
40
  ```
41
  python -m <path.to.enjoy.module> --algo=APPO --env=doom_deadly_corridor --train_dir=./train_dir --experiment=deadly_corridor_experiment
42
  ```
43
-
44
-
45
- You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag.
46
- See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
47
 
48
  ## Training with this model
49
 
@@ -52,5 +47,4 @@ To continue training with this model, use the `train` script corresponding to th
52
  python -m <path.to.train.module> --algo=APPO --env=doom_deadly_corridor --train_dir=./train_dir --experiment=deadly_corridor_experiment --restart_behavior=resume --train_for_env_steps=10000000000
53
  ```
54
 
55
- Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
56
 
 
20
  verified: false
21
  ---
22
 
23
+ An **APPO** model trained on the **doom_deadly_corridor** environment.
24
 
25
+ This model was trained using Sample-Factory 2.1.1
 
26
 
27
 
28
  ## Downloading the model
 
39
  ```
40
  python -m <path.to.enjoy.module> --algo=APPO --env=doom_deadly_corridor --train_dir=./train_dir --experiment=deadly_corridor_experiment
41
  ```
 
 
 
 
42
 
43
  ## Training with this model
44
 
 
47
  python -m <path.to.train.module> --algo=APPO --env=doom_deadly_corridor --train_dir=./train_dir --experiment=deadly_corridor_experiment --restart_behavior=resume --train_for_env_steps=10000000000
48
  ```
49
 
 
50