Upload . with huggingface_hub

README.md

@@ -5,7 +5,7 @@ tags:
 - reinforcement-learning
 - sample-factory
 model-index:
-- name: APPO
+- name: PPO
   results:
   - task:
       type: reinforcement-learning
@@ -15,12 +15,12 @@ model-index:
       type: pick-place-v2
     metrics:
     - type: mean_reward
-      value: 23.31 +/- 11.58
+      value: 24.42 +/- 7.77
       name: mean_reward
       verified: false
 ---
 
-A(n) **APPO** model trained on the **pick-place-v2** environment.
+A(n) **PPO** model trained on the **pick-place-v2** environment.
 
 This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory.
 Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
@@ -38,7 +38,7 @@ python -m sample_factory.huggingface.load_from_hub -r qgallouedec/pick-place-v2-
 
 To run the model after download, use the `enjoy` script corresponding to this environment:
 ```
-python -m enjoy --algo=APPO --env=pick-place-v2 --train_dir=./train_dir --experiment=pick-place-v2-sf
+python -m enjoy --algo=PPO --env=pick-place-v2 --train_dir=./train_dir --experiment=pick-place-v2-sf
 ```
 
 
@@ -49,7 +49,7 @@ See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
 
 To continue training with this model, use the `train` script corresponding to this environment:
 ```
-python -m train --algo=APPO --env=pick-place-v2 --train_dir=./train_dir --experiment=pick-place-v2-sf --restart_behavior=resume --train_for_env_steps=10000000000
+python -m train --algo=PPO --env=pick-place-v2 --train_dir=./train_dir --experiment=pick-place-v2-sf --restart_behavior=resume --train_for_env_steps=10000000000
 ```
 
 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.

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4028f35554118c1e424ec2f13d27c0b0ddf9995bb833671c40b104e4c3af1c83
-size 3398790
+oid sha256:8f9f8146633325df4e663a71d66827f81598ffa38b7bee2b3b8305e1f5810e00
+size 3419609