Pinned Loading
-
highway-rl
highway-rl PublicPPO with TTC-based reward shaping on merge-v0. PPO with time-to-collision reward shaping on highway-env merge-v0. Multi-seed evaluation shows 58% relative reduction in crash rate (p=0.024) vs spars…
Python
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.