Optimality Inductive Biases and Agnostic Guidelines for Offline Reinforcement Learning. (arXiv:2107.01407v2 [cs.LG] UPDATED)

The performance of state-of-the-art offline RL methods varies widely over the
spectrum of dataset qualities, ranging from far-from-optimal random data to
close-to-optimal expert demonstrations. We re-implement these methods to test
their reproducibility, and show that when a given method outperforms the others
on one end of the spectrum, it never does on the other end. This prevents us
from naming a victor across the board. We attribute the asymmetry to the amount
of inductive bias injected into the agent to …

arxiv biases guidelines learning reinforcement learning