activity
20192026
most citedFeasible Actor-Critic: Constrained Reinforcement Learning for Ensuring Statewise Safety

19 citations · 36 across the 17 of their papers we have counts for

collaborators
Showing cs.LGShow all

10 papers · 1 filter

cs.LG2026

Beyond Token-Local Imitation: Reward-Compatible Temporal Credit Assignment for On-Policy Distillation

Shiqi Liu, Zeyu He, Letian Tao +9

On-policy distillation (OPD) has emerged as an effective approach for large language model post-training, yet existing objectives face a trade-off between objective fidelity and op…

cs.LG2026

On the Identifiability of Controlled World Models

Xiangteng Zhang, Yang Guan, Bo Zhang +3

World model serves as a promising tool to infer environment dynamics under high-dimensional observations and candidate actions. Recently, LeCun's JEPA provides a compelling framewo…

cs.LG2026

FAST: A Framework for Aligned Sampling and Training in Parallel Reinforcement Learning for Autonomous Driving

Bonan Wang, Letian Tao, Bin Shuai +7

Deep reinforcement learning is pivotal for closed-loop autonomous driving yet remains constrained by severe bottlenecks in sampling efficiency. Standard parallel sampling mitigates…

cs.LG2021

Model-based Chance-Constrained Reinforcement Learning via Separated Proportional-Integral Lagrangian

Baiyu Peng, Jingliang Duan, Jianyu Chen +6

Safety is essential for reinforcement learning (RL) applied in the real world. Adding chance constraints (or probabilistic constraints) is a suitable way to enhance RL safety under…

cs.LG202119 cited

Feasible Actor-Critic: Constrained Reinforcement Learning for Ensuring Statewise Safety

Haitong Ma, Yang Guan, Shegnbo Eben Li +3

The safety constraints commonly used by existing safe reinforcement learning (RL) methods are defined only on expectation of initial states, but allow each certain state to be unsa…

cs.LG2021

Integrated Decision and Control: Towards Interpretable and Computationally Efficient Driving Intelligence

Yang Guan, Yangang Ren, Qi Sun +5

Decision and control are core functionalities of high-level automated vehicles. Current mainstream methods, such as functionality decomposition and end-to-end reinforcement learnin…