ppo-dash
ppo-dash copied to clipboard
Round 2 Code
Hey Joe,
I was wondering if you could make your round 2 code available. Or how big of a deal would it be to upgrade this code from OT v1.3 to v3.1?
Quick question on the side, --num-env-steps=500,000,00 refers to the overall taken steps to sample data from the 32 environment instances, right?