cleanba icon indicating copy to clipboard operation
cleanba copied to clipboard

verified publisher icon vwxyzjn
→

Metadata

CleanRL's implementation of DeepMind's Podracer Sebulba Architecture for Distributed DRL

Results 2 cleanba issues
Sort by recently updated
recently updated
newest added

Missing clipped value loss in PPO implementation

1 comment

Hi @vwxyzjn , This codebase is great, thanks for the hard work! I've been using it to run baseline experiments in procgen, and I've noticed that your implementation of PPO...

francelico avatar francelico

Using envpool's xla step function

Hi @vwxyzjn I'm using cleanba as a basis when implementing RL algorithms. I was wondering why you're not using envpool's jittable step function (i.e. as in https://github.com/vwxyzjn/cleanrl/blob/master/cleanrl/ppo_atari_envpool_xla_jax_scan.py). Is the speed-up...

francelico avatar francelico

← Metadata

87
Stars
8
Forks
Watchers

Owner

verified publisher icon vwxyzjn

Metadata

CleanRL's implementation of DeepMind's Podracer Sebulba Architecture for Distributed DRL

Back