Sample-Efficient Preference-based Reinforcement Learning with Dynamics Aware Rewards

Preference-based reinforcement learning (PbRL) aligns a robot behavior with human preferences via a reward function learned from binary feedback over agent behaviors. We show that encoding environment dynamics in the reward function improves the sample efficiency of PbRL by an order of magnitude. In our experiments we iterate between: (1) encoding environment dynamics in a state-action representation $z^{sa}$ via a self-supervised temporal consistency task, and (2) bootstrapping the preference-based reward function from $z^{sa}$, which results in faster policy learning and better final policy performance. For example, on quadruped-walk, walker-walk, and cheetah-run, with 50 preference labels we achieve the same performance as existing approaches with 500 preference labels, and we recover $83%$ and $66%$ of ground truth reward policy performance versus only $38%$ and $21%$ without environment dynamics. The performance gains demonstrate that explicitly encoding environment dynamics improves preference-learned reward functions.