4 papers
Distributional Soft Bellman Operator under the Cramér Geometry
Keru Wang, Yixin Deng, Yao Lyu +2
Distributional soft policy iteration (DSPI) provides an important framework for combining distributional reinforcement learning (DRL) with maximum-entropy control, in which the pol…
A Spectral Revisit of the Distributional Bellman Operator under the Cramér Metric
Keru Wang, Yixin Deng, Yao Lyu +2
Distributional reinforcement learning (DRL) studies the evolution of full return distributions under Bellman updates rather than focusing on expected values. A classical result is…
Dataset Clustering for Improved Offline Policy Learning
Qiang Wang, Yixin Deng, Francisco Roldan Sanchez +4
Offline policy learning aims to discover decision-making policies from previously-collected datasets without additional online interactions with the environment. As the training da…
Learning and reusing primitive behaviours to improve Hindsight Experience Replay sample efficiency
Francisco Roldan Sanchez, Qiang Wang, David Cordova Bulens +3
Hindsight Experience Replay (HER) is a technique used in reinforcement learning (RL) that has proven to be very efficient for training off-policy RL-based agents to solve goal-base…