VUBIR (Vrije Universiteit Brussel) · 2016 · 59 citations · 21 references
ComputingComputer ScienceArtificial IntelligenceMachine LearningRoboticsLearning From DemonstrationReinforcement LearningDemonstration-based Policy LearningFeedbackInverse Reinforcement LearningModel-free AlgorithmsModel-free Reinforcement LearningPotential-based Reward ShapingReward Learning From DemonstrationReward Shaping
Model-free episodic reinforcement learning problems define the environment reward with functions that often provide only sparse information throughout the task. Consequently, agents are not given enough feedback about the fitness of their actions until the task ends with success or failure. Previous work addresses this problem with reward shaping. In this paper we introduce a novel approach to improve model-free reinforcement learning agents' performance with a three step approach. Specifically, we collect demonstration data, use the data to recover a linear function using inverse reinforcement learning and we use the recovered function for potential-based reward shaping. Our approach is model-free and scalable to high dimensional domains. To show the scalability of our approach we present two sets of experiments in a two dimensional Maze domain, and the 27 dimensional Mario AI domain. We compare the performance of our algorithm to previously introduced reinforcement learning from demonstration algorithms. Our experiments show that our approach outperforms the state-of-the-art in cumulative reward, learning rate and asymptotic performance.
21
The Behavior of Organisms: An Experimental Analysis
F. Nowell Jones, B. F. Skinner · The American Journal of Psychology · 1939 · 4.4K citations
Apprenticeship learning via inverse reinforcement learning
Pieter Abbeel, Andrew Y. Ng · 2004 · 2.9K citations