Self-Imitation Learning via Generalized Lower Bound Q-learning

2020/06/12 by Tang, Yunhao · 1 citation
#FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · doi:10.48550/arxiv.2006.07442

Abstract

Self-imitation learning motivated by lower-bound Q-learning is a novel and effective approach for off-policy learning. In this work, we propose a n-step lower bound which generalizes the original return-based lower-bound Q-learning, and introduce a new family of self-imitation learning algorithms. To provide a formal motivation for the potential performance gains provided by self-imitation learning, we show that n-step lower bound Q-learning achieves a trade-off between fixed point bias and contraction rate, drawing close connections to the popular uncorrected n-step Q-learning. We finally show that n-step lower bound Q-learning is a more robust alternative to return-based self-imitation learning and uncorrected n-step, over a wide range of continuous control benchmark tasks.

Cited by

• Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning
• GCHR : Goal-Conditioned Hindsight Regularization for Sample-Efficient Reinforcement Learning

Related

• Augmented Q Imitation Learning (AQIL)
• Quantile Filtered Imitation Learning
• IQ-Learn: Inverse soft-Q Learning for Imitation
• Inverse Q-Learning Done Right: Offline Imitation Learning in Q^π-Realizable MDPs
• Scalable Causal Imitation Learning