ACTRCE: Augmenting Experience via Teacher's Advice For Multi-Goal Reinforcement Learning
This addresses the challenge of sparse rewards in RL for multi-goal tasks, offering a novel approach with language-based goal representation, though it builds incrementally on HER.
The paper tackles the sparse reward problem in reinforcement learning by introducing ACTRCE, which extends Hindsight Experience Replay using natural language as a goal representation, enabling efficient learning in 3D navigation tasks where HER failed and allowing generalization to unseen instructions and lexicons.
Sparse reward is one of the most challenging problems in reinforcement learning (RL). Hindsight Experience Replay (HER) attempts to address this issue by converting a failed experience to a successful one by relabeling the goals. Despite its effectiveness, HER has limited applicability because it lacks a compact and universal goal representation. We present Augmenting experienCe via TeacheR's adviCE (ACTRCE), an efficient reinforcement learning technique that extends the HER framework using natural language as the goal representation. We first analyze the differences among goal representation, and show that ACTRCE can efficiently solve difficult reinforcement learning problems in challenging 3D navigation tasks, whereas HER with non-language goal representation failed to learn. We also show that with language goal representations, the agent can generalize to unseen instructions, and even generalize to instructions with unseen lexicons. We further demonstrate it is crucial to use hindsight advice to solve challenging tasks, and even small amount of advice is sufficient for the agent to achieve good performance.