DIPPER: Direct Preference Optimization to Accelerate Primitive-Enabled Hierarchical Reinforcement Learning

TL;DR

DIPPER introduces a hierarchical reinforcement learning method that uses direct preference optimization and primitive-informed regularization to efficiently learn complex robotics tasks from limited human preferences, outperforming existing methods.

Contribution

The paper presents DIPPER, a novel hierarchical RL approach combining direct preference optimization with primitive-informed regularization, addressing efficiency and subgoal generation issues.

Findings

DIPPER outperforms hierarchical and non-hierarchical baselines.

It improves computational efficiency over standard preference-based methods.

It mitigates non-stationarity and infeasible subgoal issues in hierarchical RL.

Abstract

Learning control policies to perform complex robotics tasks from human preference data presents significant challenges. On the one hand, the complexity of such tasks typically requires learning policies to perform a variety of subtasks, then combining them to achieve the overall goal. At the same time, comprehensive, well-engineered reward functions are typically unavailable in such problems, while limited human preference data often is; making efficient use of such data to guide learning is therefore essential. Methods for learning to perform complex robotics tasks from human preference data must overcome both these challenges simultaneously. In this work, we introduce DIPPER: Direct Preference Optimization to Accelerate Primitive-Enabled Hierarchical Reinforcement Learning, an efficient hierarchical approach that leverages direct preference optimization to learn a higher-level policy and reinforcement learning to learn a lower-level policy. DIPPER enjoys improved computational efficiency due to its use of direct preference optimization instead of standard preference-based approaches such as reinforcement learning from human feedback, while it also mitigates the well-known hierarchical reinforcement learning issues of non-stationarity and infeasible subgoal generation due to our use of primitive-informed regularization inspired by a novel bi-level optimization formulation of the hierarchical reinforcement learning problem. To validate our approach, we perform extensive experimental analysis on a variety of challenging robotics tasks, demonstrating that DIPPER outperforms hierarchical and non-hierarchical baselines, while ameliorating the non-stationarity and infeasible subgoal generation issues of hierarchical reinforcement learning.