2023 · 28 citations · 22 references
ComputingComputer ScienceArtificial IntelligenceKnowledge TransferMachine LearningReinforcement LearningTransfer LearningMulti-task Reinforcement LearningPotential-based Reward ShapingReinforcement Learning TheoryReinforcement Learning TransferReward ShapingReward-based LearningTransfer Reinforcement Learning
Potential-based reward shaping (PBRS) is a particular category of machine learning methods that aims to improve the learning speed of a reinforcement learning agent by extracting and utilizing extra knowledge while performing a task. There are two steps in the transfer learning process: extracting knowledge from previously learned tasks and transferring that knowledge to use it in a target task. The latter step is well discussed in the literature, with various methods being proposed for it, while the former has been explored less. With this in mind, the type of knowledge that is transmitted is very important and can lead to considerable improvement. Among the literature of both transfer learning and potential-based reward shaping, a subject that has never been addressed is the knowledge gathered during the learning process itself. In this paper, we presented a novel potential-based reward shaping method that attempted to extract knowledge from the learning process. The proposed method extracts knowledge from episodes' cumulative rewards. The proposed method has been evaluated in the Arcade learning environment, and the results indicate an improvement in the learning process in both the single-task and the multi-task reinforcement learner agents.
22
Reinforcement Learning: An Introduction
Richard S. Sutton, Andy Barto · IEEE Transactions on Neural Networks · 1998 · 27.1K citations
Christopher J. Watkins, Peter Dayan · Machine Learning · 1992 · 9K citations · Full text
Christopher J. Watkins, Peter Dayan · Machine Learning · 1992 · 3.7K citations