Addressing the issue of stochastic environments and local decision-making in multi-objective reinforcement learning

TL;DR

This paper investigates how stochastic environments and local decision-making affect the ability of multi-objective reinforcement learning algorithms to learn optimal policies, highlighting the impact of noisy Q-value estimates and proposing improvements.

Contribution

It identifies the influence of environment stochasticity and utility functions on MORL Q-learning performance and evaluates variants incorporating global statistics and option learning.

Findings

Reward signal design improves baseline performance

Global statistics variant outperforms baseline but is not fully effective

Option learning guarantees convergence but lacks scalability

Abstract

Multi-objective reinforcement learning (MORL) is a relatively new field which builds on conventional Reinforcement Learning (RL) to solve multi-objective problems. One of common algorithm is to extend scalar value Q-learning by using vector Q values in combination with a utility function, which captures the user's preference for action selection. This study follows on prior works, and focuses on what factors influence the frequency with which value-based MORL Q-learning algorithms learn the optimal policy for an environment with stochastic state transitions in scenarios where the goal is to maximise the Scalarised Expected Return (SER) - that is, to maximise the average outcome over multiple runs rather than the outcome within each individual episode. The analysis of the interaction between stochastic environment and MORL Q-learning algorithms run on a simple Multi-objective Markov decision process (MOMDP) Space Traders problem with different variant versions. The empirical evaluations show that well designed reward signal can improve the performance of the original baseline algorithm, however it is still not enough to address more general environment. A variant of MORL Q-Learning incorporating global statistics is shown to outperform the baseline method in original Space Traders problem, but remains below 100 percent effectiveness in finding the find desired SER-optimal policy at the end of training. On the other hand, Option learning is guarantied to converge to desired SER-optimal policy but it is not able to scale up to solve more complex problem in real-life. The main contribution of this thesis is to identify the extent to which the issue of noisy Q-value estimates impacts on the ability to learn optimal policies under the combination of stochastic environments, non-linear utility and a constant learning rate.