Backward Learning for Goal-Conditioned Policies

arXiv:2312.05044v2 Announce Type: replace
Abstract: Can we learn policies in reinforcement learning without rewards? Can we learn a policy just by trying to reach a goal state? We answer these questions positively by proposing a multi-step procedure that first learns a world model that goes backward in time, secondly generates goal-reaching backward trajectories, thirdly improves those sequences using shortest path finding algorithms, and finally trains a neural network policy by imitation learning. We evaluate our method on a deterministic maze …

abstract arxiv cs.ai cs.lg learn policies policy questions reinforcement reinforcement learning state type world world model