Talks

Information will be updated here prior to workshop.

Papers

• Second-Order Actor-Critic Methods for Discounted MDPs via Policy Hessian Decomposition
  Sanjeev Manivannan, Shuban V

• When are LLMs Sufficient Policy Optimizers for Sequential RL Tasks?
  Stephane Hatgis-Kessell, Emma Brunskill

• Drop the Act: Probe-Filtered RL for Faithful Chain-of-Thought Reasoning
  Swapnil Parekh

• Reward Geometry After Abstraction: Representation-Relative Reward Equivalence for Robotic Manipulation
  Manoj Saravanan

• Towards Scalable Multi-Task Reinforcement Learning with Large Decision Models
  Thibaut Kulak

• Decoupling Task Inference in Offline Meta-RL
  Chanseok Kang, Jinwoo Lee, Guntae Bae

• Distributionally Robust Multi-Task Reinforcement Learning via Adaptive Task Sampling
  Nicholas E. Corrado, Wenyuan Huang, Josiah P. Hanna

• A Framework for Designing Reward Functions: From Objectives to Features to Human-Aligned Reward Functions
  Di Yang Shi, W. Bradley Knox

• Behavior-Consistent Deep Reinforcement Learning
  Marcel Hussing, Liv G. d'Aliberti, Claas A Voelcker, Benjamin Eysenbach, Eric Eaton

• Performance Variation in Deep Reinforcement Learning
  Haruto Tanaka, A. Rupam Mahmood

• Bayesian Swarm Training: Stable Online Hyperparameter Scheduling for Deep Reinforcement Learning
  Jorge Calvillo-Rodriguez, Carlos Ignacio Hernández Castellanos, Katya Rodriguez-Vazquez

• Successor Features Enable Transfer from Behaviorally Diverse Tasks
  Aasmaan Gupta, G V Vijay Raj, Raghuram Bharadwaj Diddigi