Hindsight Task Relabelling: Experience Replay for Sparse Reward Meta-RL
Packer, Charles, Abbeel, Pieter, Gonzalez, Joseph E.
–arXiv.org Artificial Intelligence
Meta-reinforcement learning (meta-RL) has proven to be a successful framework for leveraging experience from prior tasks to rapidly learn new related tasks, however, current meta-RL approaches struggle to learn in sparse reward environments. Although existing meta-RL algorithms can learn strategies for adapting to new sparse reward tasks, the actual adaptation strategies are learned using hand-shaped reward functions, or require simple environments where random exploration is sufficient to encounter sparse reward. In this paper, we present a formulation of hindsight relabeling for meta-RL, which relabels experience during meta-training to enable learning to learn entirely using sparse reward. We demonstrate the effectiveness of our approach on a suite of challenging sparse reward goal-reaching environments that previously required dense reward during meta-training to solve. Our approach solves these environments using the true sparse reward function, with performance comparable to training with a proxy dense reward function.
arXiv.org Artificial Intelligence
Dec-1-2021
- Country:
- Oceania > Australia
- New South Wales > Sydney (0.04)
- Europe > Germany
- North Rhine-Westphalia > Upper Bavaria > Munich (0.04)
- Oceania > Australia
- Genre:
- Research Report (1.00)
- Industry:
- Information Technology > Security & Privacy (0.46)
- Technology: