Intrinsically Motivated Hierarchical Policy Learning in Multi-objective Markov Decision Processes

TL;DR

This paper introduces a dual-phase intrinsically motivated reinforcement learning approach that learns generic skills to adaptively solve multi-objective Markov decision processes in non-stationary environments, outperforming existing methods.

Contribution

The paper proposes a novel dual-phase intrinsically motivated reinforcement learning method that learns generic skills for hierarchical policy adaptation in changing environments.

Findings

Significantly outperforms state-of-the-art methods in dynamic robotics tasks.

Effectively learns a generic skill set for non-stationary environments.

Demonstrates improved policy coverage and adaptability.

Abstract

Multi-objective Markov decision processes are sequential decision-making problems that involve multiple conflicting reward functions that cannot be optimized simultaneously without a compromise. This type of problems cannot be solved by a single optimal policy as in the conventional case. Alternatively, multi-objective reinforcement learning methods evolve a coverage set of optimal policies that can satisfy all possible preferences in solving the problem. However, many of these methods cannot generalize their coverage sets to work in non-stationary environments. In these environments, the parameters of the state transition and reward distribution vary over time. This limitation results in significant performance degradation for the evolved policy sets. In order to overcome this limitation, there is a need to learn a generic skill set that can bootstrap the evolution of the policy coverage set for each shift in the environment dynamics therefore, it can facilitate a continuous learning process. In this work, intrinsically motivated reinforcement learning has been successfully deployed to evolve generic skill sets for learning hierarchical policies to solve multi-objective Markov decision processes. We propose a novel dual-phase intrinsically motivated reinforcement learning method to address this limitation. In the first phase, a generic set of skills is learned. While in the second phase, this set is used to bootstrap policy coverage sets for each shift in the environment dynamics. We show experimentally that the proposed method significantly outperforms state-of-the-art multi-objective reinforcement methods in a dynamic robotics environment.