MADDM: Multi-Advisor Dynamic Binary Decision-Making by Maximizing the Utility

no code implementations • 15 May 2023 • Zhaori Guo, Timothy J. Norman, Enrico H. Gerding

In practice, however, gathering answers from a set of advisors has a cost.

Decision Making

Multi-trainer Interactive Reinforcement Learning System

no code implementations • 14 Oct 2022 • Zhaori Guo, Timothy J. Norman, Enrico H. Gerding

In this paper, we propose a more effective interactive reinforcement learning system by introducing multiple trainers, namely Multi-Trainer Interactive Reinforcement Learning (MTIRL), which could aggregate the binary feedback from multiple non-perfect trainers into a more reliable reward for an agent training in a reward-sparse environment.

reinforcement-learning Reinforcement Learning (RL)