Monte Carlo Tree Search Algorithms for Risk-Aware and Multi-Objective Reinforcement Learning

TL;DR

This paper introduces two novel Monte Carlo tree search algorithms designed for risk-aware and multi-objective reinforcement learning, effectively handling the distribution of returns rather than just their expected value.

Contribution

The paper proposes NLU-MCTS and DMCTS algorithms that optimize policies for nonlinear utility functions and approximate return distributions, advancing risk-aware and multi-objective RL.

Findings

Both algorithms outperform state-of-the-art methods in expected utility optimization.

DMCTS effectively uses Thompson sampling for risk-aware decision making.

The methods are applicable in single-execution scenarios like medical treatments.

Abstract

In many risk-aware and multi-objective reinforcement learning settings, the utility of the user is derived from a single execution of a policy. In these settings, making decisions based on the average future returns is not suitable. For example, in a medical setting a patient may only have one opportunity to treat their illness. Making decisions using just the expected future returns -- known in reinforcement learning as the value -- cannot account for the potential range of adverse or positive outcomes a decision may have. Therefore, we should use the distribution over expected future returns differently to represent the critical information that the agent requires at decision time by taking both the future and accrued returns into consideration. In this paper, we propose two novel Monte Carlo tree search algorithms. Firstly, we present a Monte Carlo tree search algorithm that can compute policies for nonlinear utility functions (NLU-MCTS) by optimising the utility of the different possible returns attainable from individual policy executions, resulting in good policies for both risk-aware and multi-objective settings. Secondly, we propose a distributional Monte Carlo tree search algorithm (DMCTS) which extends NLU-MCTS. DMCTS computes an approximate posterior distribution over the utility of the returns, and utilises Thompson sampling during planning to compute policies in risk-aware and multi-objective settings. Both algorithms outperform the state-of-the-art in multi-objective reinforcement learning for the expected utility of the returns.