issues
search
bmazoure
/
ppo_jax
Jax implementation of Proximal Policy Optimization (PPO) specifically tuned for Procgen, with benchmarked results and saved model weights on all environments.
48
stars
1
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Training speed and computation cost
#3
kaixin96
opened
2 years ago
0
PPO's performance
#2
vwxyzjn
opened
2 years ago
1
[Bug] Run epoch over multiple minibatches
#1
RobertTLange
closed
2 years ago
2