ODICE: Revealing the Mystery of Distribution Correction Estimation via Orthogonal-gradient Updateby Liyuan Mao, Haoran Xu,…
Control in Stochastic Environment with Delays: A Model-based Reinforcement Learning Approachby Zhiyuan Yao, Ionut Florescu,…
Introducing PetriRL: An Innovative Framework for JSSP Resolution Integrating Petri nets and Event-based Reinforcement Learningby…
Scheduled Curiosity-Deep Dyna-Q: Efficient Exploration for Dialog Policy Learningby Xuecheng Niu, Akinori Ito, Takashi NoseFirst…
Behind the Myth of Exploration in Policy Gradientsby Adrien Bolland, Gaspard Lambrechts, Damien ErnstFirst submitted…
Causal Coordinated Concurrent Reinforcement Learningby Tim Tse, Isaac Chan, Zhitang ChenFirst submitted to arxiv on:…
A Policy Gradient Primal-Dual Algorithm for Constrained MDPs with Uniform PAC Guaranteesby Toshinori Kitamura, Tadashi…
Simplifying Latent Dynamics with Softly State-Invariant World Modelsby Tankred Saanum, Peter Dayan, Eric SchulzFirst submitted…
Zero-Shot Reinforcement Learning via Function Encodersby Tyler Ingebrand, Amy Zhang, Ufuk TopcuFirst submitted to arxiv…
CORE: Towards Scalable and Efficient Causal Discovery with Reinforcement Learningby Andreas W.M. Sauter, Nicolò Botteghi,…