5 papers
Proximal Action Replacement for Behavior Cloning Actor-Critic in Offline Reinforcement Learning
Jinzong Dong, Wei Huang, Jianshu Zhang +5
Offline reinforcement learning (RL), which optimizes policies using a previously collected static dataset, is an important branch of RL. A popular and promising approach is to regu…
FastForward Pruning: Efficient LLM Pruning via Single-Step Reinforcement Learning
Xin Yuan, Siqi Li, Jiateng Wei +7
Pruning is an effective method for compressing Large Language Models, but finding an optimal, non-uniform layer-wise sparsity allocation remains a key challenge. While heuristic me…
RuN: Residual Policy for Natural Humanoid Locomotion
Qingpeng Li, Chengrui Zhu, Yanming Wu +4
Enabling humanoid robots to achieve natural and dynamic locomotion across a wide range of speeds, including smooth transitions from walking to running, presents a significant chall…
RoboArena: Distributed Real-World Evaluation of Generalist Robot Policies
Pranav Atreya, Karl Pertsch, Tony Lee +29
Comprehensive, unbiased, and comparable evaluation of modern generalist policies is uniquely challenging: existing approaches for robot benchmarking typically rely on heavy standar…
Learning to Recover for Safe Reinforcement Learning
Haoyu Wang, Xin Yuan, Qinqing Ren
Safety controllers is widely used to achieve safe reinforcement learning. Most methods that apply a safety controller are using handcrafted safety constraints to construct the safe…