Bandit-Based Policy Invariant Explicit Shaping for Incorporating External Advice in Reinforcement Learning

no code implementations • 14 Apr 2023 • Yash Satsangi, Paniz Behboudian

A key challenge for a reinforcement learning (RL) agent is to incorporate external/expert1 advice in its learning.

reinforcement-learning Reinforcement Learning (RL)

Useful Policy Invariant Shaping from Arbitrary Advice

no code implementations • 2 Nov 2020 • Paniz Behboudian, Yash Satsangi, Matthew E. Taylor, Anna Harutyunyan, Michael Bowling

Furthermore, if the reward is constructed from a potential function, the optimal policy is guaranteed to be unaltered.