A Robust Policy Bootstrapping Algorithm for Multi-objective Reinforcement Learning in Non-stationary Environments
Abdelfattah, Sherif, Kasmarik, Kathryn, Hu, Jiankun
–arXiv.org Artificial Intelligence
Multi-objective Markov decision processes are a special kind of multi-objective optimization problem that involves sequential decision making while satisfying the Markov property of stochastic processes. Multi-objective reinforcement learning methods address this problem by fusing the reinforcement learning paradigm with multi-objective optimization techniques. One major drawback of these methods is the lack of adaptability to non-stationary dynamics in the environment. This is because they adopt optimization procedures that assume stationarity to evolve a coverage set of policies that can solve the problem. This paper introduces a developmental optimization approach that can evolve the policy coverage set while exploring the preference space over the defined objectives in an online manner. We propose a novel multi-objective reinforcement learning algorithm that can robustly evolve a convex coverage set of policies in an online manner in non-stationary environments. We compare the proposed algorithm with two state-of-the-art multi-objective reinforcement learning algorithms in stationary and non-stationary environments. Results showed that the proposed algorithm significantly outperforms the existing algorithms in non-stationary environments while achieving comparable results in stationary environments.
arXiv.org Artificial Intelligence
Aug-17-2023
- Country:
- Oceania > Australia
- New South Wales (0.04)
- Australian Capital Territory > Canberra (0.04)
- North America > United States
- Massachusetts > Suffolk County > Boston (0.04)
- Europe > Netherlands
- North Holland > Amsterdam (0.04)
- Asia > Taiwan
- Taiwan Province > Taipei (0.04)
- Oceania > Australia
- Genre:
- Research Report
- Experimental Study (1.00)
- New Finding (0.68)
- Research Report