Rewriting History with Inverse RL: Hindsight Inference for Policy Improvement

Abstract

Multi-task reinforcement learning (RL) aims to simultaneously learn policies for solving many tasks. Several prior works have found that relabeling past experience with different reward functions can improve sample efficiency. Relabeling methods typically ask: if, in hindsight, we assume that our experience was optimal for some task, for what task was it optimal? In this paper, we show that hindsight relabeling is inverse RL, an observation that suggests that we can use inverse RL in tandem for RL algorithms to efficiently solve many tasks. We use this idea to generalize goal-relabeling techniques from prior work to arbitrary classes of tasks. Our experiments confirm that relabeling data using inverse RL accelerates learning in general multi-task settings, including goal-reaching, domains with discrete sets of rewards, and those with linear reward functions.

References in corpus (4)

• Theoretical Models of Learning to Learn
• DeepMind Control Suite
• Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables
• Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning

Cited by in corpus (6)

• Hindsight Goal Ranking on Replay Buffer for Sparse Reward Environment
• C-Learning: Learning to Achieve Goals via Recursive Classification
• Automating Reinforcement Learning with Example-based Resets
• Pessimistic Value Iteration for Multi-Task Data Sharing in Offline Reinforcement Learning
• Conservative Data Sharing for Multi-Task Offline Reinforcement Learning
• Wish you were here: Hindsight Goal Selection for long-horizon dexterous manipulation