An Empirical Investigation of Value-Based Multi-objective Reinforcement Learning for Stochastic Environments
Abstract: One common approach to solve multi-objective reinforcement learning (MORL) problems is to extend conventional Q-learning by using vector Q-values in combination with a utility function. However issues can arise with this approach in the context of stochastic environments, particularly when optimising for the Scalarised Expected Reward (SER) criterion. This paper extends prior research, providing a detailed examination of the factors influencing the frequency with which value-based MORL Q-learning algorithms learn the SER-optimal policy for an environment with stochastic state transitions. We empirically examine several variations of the core multi-objective Q-learning algorithm as well as reward engineering approaches, and demonstrate the limitations of these methods. In particular, we highlight the critical impact of the noisy Q-value estimates issue on the stability and convergence of these algorithms.
- Ding K (2022) Addressing the issue of stochastic environments and local decision-making in multi-objective reinforcement learning. arXiv preprint arXiv:221108669
- Dornheim J (2022) gTLO: A generalized and non-linear multi-objective deep reinforcement learning approach. arXiv preprint arXiv:220404988
- Sutton RS, Barto AG (2018) Reinforcement learning: An introduction. MIT press
- Tercan A (2022) Solving MDPs with thresholded lexicographic ordering using reinforcement learning. PhD thesis, Colorado State University
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.