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 benchmark tasks.
Yunhao Tang (Columbia University)
I am a PhD student at Columbia IEOR. My research interests are reinforcement learning and approximate inference.
More from the Same Authors
2021 Poster: Unifying Gradient Estimators for Meta-Reinforcement Learning via Off-Policy Evaluation »
Yunhao Tang · Tadashi Kozuno · Mark Rowland · Remi Munos · Michal Valko
2019 Poster: From Complexity to Simplicity: Adaptive ES-Active Subspaces for Blackbox Optimization »
Krzysztof M Choromanski · Aldo Pacchiano · Jack Parker-Holder · Yunhao Tang · Vikas Sindhwani