Support MTBench (#15)
This PR incorporates MTBench into the current codebase, as a good demonstration that shows how to use FastTD3 for multi-task setup. - Add support for MTBench along with its wrapper - Add support for per-task reward normalizer useful for multi-task RL, motivated by BRC paper (https://arxiv.org/abs/2505.23150v1)
This commit is contained in:
@@ -0,0 +1,15 @@
|
||||
gymnasium<1.0.0
|
||||
jax-jumpy==1.0.0 ; python_version >= "3.8" and python_version < "3.11"
|
||||
matplotlib
|
||||
moviepy
|
||||
numpy<2.0
|
||||
pandas
|
||||
protobuf
|
||||
pygame
|
||||
stable-baselines3
|
||||
tqdm
|
||||
wandb
|
||||
torchrl==0.5.0
|
||||
tensordict==0.5.0
|
||||
tyro
|
||||
loguru
|
||||
Reference in New Issue
Block a user