4 papers · 1 filter
Adaptive Layerwise Perturbation: Unifying Off-Policy Corrections for LLM RL
Chenlu Ye, Xuanchang Zhang, Yifan Hao +6
Off-policy problems such as policy staleness and training--inference mismatch have become a major bottleneck for training stability and further exploration in LLM RL. The distribut…
Mitigating Estimation Bias with Representation Learning in TD Error-Driven Regularization
Haohui Chen, Zhiyong Chen, Aoxiang Liu +1
Deterministic policy gradient algorithms for continuous control suffer from value estimation biases that degrade performance. While double critics reduce such biases, the explorati…
Mildly Conservative Regularized Evaluation for Offline Reinforcement Learning
Haohui Chen, Zhiyong Chen
Offline reinforcement learning (RL) seeks to learn optimal policies from static datasets without further environment interaction. A key challenge is the distribution shift between…
Double Actor-Critic with TD Error-Driven Regularization in Reinforcement Learning
Haohui Chen, Zhiyong Chen, Aoxiang Liu +1
To obtain better value estimation in reinforcement learning, we propose a novel algorithm based on the double actor-critic framework with temporal difference error-driven regulariz…