arXiv:2606. 15247v1 Announce Type: cross Abstract: The asymptotic behaviour of Monte Carlo Exploring Starts (MCES) is a long-standing open question in reinforcement learning, even in the tabular setting.
By Octave Oliviers, Glenn Vinnicombe
arXiv:2607. 28916v1 Announce Type: cross Abstract: Multistep credit assignment is critical for sample-efficient reinforcement learning, yet managing off-policy bias in Q-learning remains a fundamental challenge.
By Brett Daley
arXiv:2406.03678v2 Announce Type: replace
Abstract: On-policy reinforcement learning methods, like Trust Region Policy Optimization (TRPO) and Proximal Policy Optimization (PPO), often demand extensi...
By Yaozhong Gan, Renye Yan, Zhe Wu, Junliang Xing
GEM-MPC is a reinforcement learning method that blends MPPI planning with policy learning to balance exploration and exploitation in high-dimensional continuous control tasks. It trains a policy to clone the planner while also maintaining a KL-regularized policy that explores around the planner’s suggestions, thereby improving the synergy between planning and learning. The approach introduces Gated Prior Distillation, which selectively updates policies from stored planning distributions only when they offer better targets, reducing the influence of stale data without costly reanalysis. Across continuous-control benchmarks, GEM-MPC outperforms existing planning-based baselines while using lower computational budgets.
By Alvaro Serra-Gomez, Thomas Moerland
Pre-training followed by fine-tuning has become the dominant recipe for learning performant policies, and in value-based reinforcement learning (RL) this raises a natural question: given a pretrained policy, should the Q-function be pretrained on offline data too? Conventional wisdom suggests it should, but recent results show that online RL with a randomly-initialized Q-function can result in highly performant and reliable policies without needing to pretrain the Q-function.
arXiv:2607. 27203v1 Announce Type: new Abstract: Pre-training followed by fine-tuning has become the dominant recipe for learning performant policies, and in value-based reinforcement learning (RL) this raises a natural question: given a pretrained policy, should the Q-function be pretrained on offline data too?
By Perry Dong, Ron Polonsky, Dorsa Sadigh, Chelsea Fin