Link Search Menu Expand Document

Learning from Demonstrations using Signal Temporal Logic

Paper PDF

Authors

Aniruddh Puranic (University of Southern California)*; Jyotirmoy Deshmukh (USC); Stefanos Nikolaidis (University of Southern California)

Interactive Session

2020-11-18, 12:30 - 13:00 PST | PheedLoop Session

Abstract

Learning-from-demonstrations is an emerging paradigm to obtain effective robot control policies for complex tasks via reinforcement learning without the need to explicitly design reward functions. However, it is susceptible to imperfections in demonstrations and also raises concerns of safety and interpretability in the learned control policies. To address these issues, we use Signal Temporal Logic to evaluate and rank the quality of demonstrations. Temporal logic-based specifications allow us to create non-Markovian rewards, and also define interesting causal dependencies between tasks such as sequential task specifications. We validate our approach through experiments on discrete-world and OpenAI Gym environments, and show that our approach outperforms the state-of-the-art Maximum Causal Entropy Inverse Reinforcement Learning.

Video

Reviews and Rebuttal

Reviews & Rebuttal


Conference on Robot Learning 2020