Learning Reward Functions from a Combination of Demonstration and Evaluative Feedback

摘要

As robots become more prevalent in society, they will need to learn to act appropriately under diverse human teaching styles. We present a human-centered approach for teaching robots reward functions by using a mixture of teaching strategies when communicating action appropriateness and goal success. Our method incorporates two teaching strategies for learning: explicit action instruction and evaluative, scalar-based feedback. We demonstrate that a robot instantiating our method can learn from humans who use both kinds of strategies to train the robot in a complex navigation task that includes norm-like constraints.