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.
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.