Conference Publication Details
Mandatory Fields
Mannion, P; Devlin, S; Mason, K; Duggan, J; Howley, E
Adaptive and Learning Agents workshop (at AAMAS 2017)
Potential-Based Reward Shaping Preserves Pareto Optimal Policies
Optional Fields
Reward shaping is a well-established family of techniques that have been successfully used to improve the performance and learning speed of Reinforcement Learning agents in singleobjective problems. Here we extend the guarantees of Potential- Based Reward Shaping (PBRS) by providing theoretical proof that PBRS does not alter the true Pareto front in MORL domains. We also contribute the rst empirical studies of the e ect of PBRS in MORL problems.
Grant Details
Publication Themes
Informatics, Physical and Computational Sciences