Showing 2026Show all
3 papers · 1 filter
cs.LG2026
V-SHARE: Provable Convergence Guarantees for Advantage-based Algorithms
Kintan Saha, Hamed Masoudi, Xinyi Sheng +3
In reinforcement learning, advantage-based value-learning methods, unlike standard Q-learning, share information across actions by decomposing the action-value function into a stat…
cs.LG2026
SUN: Reaching for Novelty in Reinforcement Learning
Wenyan Yang, Arsenii Mustafin, Dominik Baumann +2
Exploration in reinforcement learning (RL) remains a fundamental challenge. Recent goal-conditioned RL strategies (which select goals to encourage broader state coverage) have show…
cs.LG2026
Ergodicity in reinforcement learning
Dominik Baumann, Erfaun Noorani, Arsenii Mustafin +5
In reinforcement learning, we typically aim to optimize the expected value of the sum of rewards an agent collects over a trajectory. However, if the process generating these rewar…