593 citations · 1.8k across the 57 of their papers we have counts for
25 papers · 1 filter
Past, Future, All at Once: Mitigating Stability-Plasticity Dilemma via Post-hoc JANUS Rectification
Zhilong Zheng, Letian Tao, Yang Guan +7
Fine-tuning foundation models on new tasks inevitably suffer from catastrophic forgetting. While existing works attempt to mitigate this on the basis of parameter-efficient fine-tu…
Momentum as Residual-Driven Multiplier Correction for Deep Learning Optimization
Zhixin Ren, Yao Lyu, Congrong Li +2
Momentum-based optimizers are widely used in modern deep learning, yet the relations among momentum recursion, update geometry, and acceleration remain only partially understood. W…
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…
Distributional Soft Bellman Operator under the Cramér Geometry
Keru Wang, Yixin Deng, Yao Lyu +2
Distributional soft policy iteration (DSPI) provides an important framework for combining distributional reinforcement learning (DRL) with maximum-entropy control, in which the pol…
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…
On the Equilibrium between Feasible Zone and Uncertain Model in Safe Exploration
Yujie Yang, Zhilong Zheng, Shengbo Eben Li
Ensuring the safety of environmental exploration is a critical problem in reinforcement learning (RL). While limiting exploration to a feasible zone has become widely accepted as a…
Exchange Policy Optimization Algorithm for Semi-Infinite Safe Reinforcement Learning
Jiaming Zhang, Yujie Yang, Haoning Wang +2
Safe reinforcement learning (RL) aims to optimize long-term performance while adhering to safety requirements. However, many practical applications involve an infinite number of co…
Rocket Landing Control with Random Annealing Jump Start Reinforcement Learning
Yuxuan Jiang, Yujie Yang, Zhiqian Lan +6
Rocket recycling is a crucial pursuit in aerospace technology, aimed at reducing costs and environmental impact in space exploration. The primary focus centers on rocket landing co…
Diffusion Actor-Critic with Entropy Regulator
Yinuo Wang, Likun Wang, Yuxuan Jiang +8
Reinforcement learning (RL) has proven highly effective in addressing complex decision-making and control tasks. However, in most traditional RL algorithms, the policy is typically…
Policy Bifurcation in Safe Reinforcement Learning
Wenjun Zou, Yao Lyu, Jie Li +7
Safe reinforcement learning (RL) offers advanced solutions to constrained optimal control problems. Existing studies in safe RL implicitly assume continuity in policy functions, wh…
Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion Model
Yinan Zheng, Jianxiong Li, Dongjie Yu +4
Safe offline RL is a promising way to bypass risky online interactions towards safe policy learning. Most existing methods only enforce soft constraints, i.e., constraining safety…
Training Multi-layer Neural Networks on Ising Machine
Xujie Song, Tong Liu, Shengbo Eben Li +3
As a dedicated quantum device, Ising machines could solve large-scale binary optimization problems in milliseconds. There is emerging interest in utilizing Ising machines to train…
Robust Safe Reinforcement Learning under Adversarial Disturbances
Zeyang Li, Chuxiong Hu, Shengbo Eben Li +2
Safety is a primary concern when applying reinforcement learning to real-world control tasks, especially in the presence of external disturbances. However, existing safe reinforcem…
Bridging the Gap between Newton-Raphson Method and Regularized Policy Iteration
Zeyang Li, Chuxiong Hu, Yunan Wang +4
Regularization is a cornerstone of modern reinforcement learning. Regularized policy iteration (RPI) provides a fundamental scheme for solving regularized Markov decision processes…
Distributional Soft Actor-Critic with Three Refinements
Jingliang Duan, Wenxuan Wang, Liming Xiao +6
Reinforcement learning (RL) has shown remarkable success in solving complex decision-making and control tasks. However, many model-free RL algorithms experience performance degrada…
Safe Reinforcement Learning with Dual Robustness
Zeyang Li, Chuxiong Hu, Yunan Wang +2
Reinforcement learning (RL) agents are vulnerable to adversarial disturbances, which can deteriorate task performance or compromise safety specifications. Existing methods either a…
Feasible Policy Iteration for Safe Reinforcement Learning
Yujie Yang, Zhilong Zheng, Shengbo Eben Li +4
Safety is the priority concern when applying reinforcement learning (RL) algorithms to real-world control problems. While policy iteration provides a fundamental algorithm for stan…
Reachability Constrained Reinforcement Learning
Dongjie Yu, Haitong Ma, Shengbo Eben Li +1
Constrained reinforcement learning (CRL) has gained significant interest recently, since safety constraints satisfaction is critical for real-world problems. However, existing CRL…
Zeroth-Order Actor-Critic: An Evolutionary Framework for Sequential Decision Problems
Yuheng Lei, Yao Lyu, Guojian Zhan +5
Evolutionary algorithms (EAs) have shown promise in solving sequential decision problems (SDPs) by simplifying them to static optimization problems and searching for the optimal po…
Learn Zero-Constraint-Violation Policy in Model-Free Constrained Reinforcement Learning
Haitong Ma, Changliu Liu, Shengbo Eben Li +3
In the trial-and-error mechanism of reinforcement learning (RL), a notorious contradiction arises when we expect to learn a safe policy: how to learn a safe policy without enough d…
Self-learned Intelligence for Integrated Decision and Control of Automated Vehicles at Signalized Intersections
Yangang Ren, Jianhua Jiang, Dongjie Yu +4
Intersection is one of the most complex and accident-prone urban scenarios for autonomous driving wherein making safe and computationally efficient decisions is non-trivial. Curren…
Joint Synthesis of Safety Certificate and Safe Control Policy using Constrained Reinforcement Learning
Haitong Ma, Changliu Liu, Shengbo Eben Li +2
Safety is the major consideration in controlling complex dynamical systems using reinforcement learning (RL), where the safety certificate can provide provable safety guarantee. A…
Mixed Policy Gradient: off-policy reinforcement learning driven jointly by data and model
Yang Guan, Jingliang Duan, Shengbo Eben Li +3
Reinforcement learning (RL) shows great potential in sequential decision-making. At present, mainstream RL algorithms are data-driven, which usually yield better asymptotic perform…
Distributional Soft Actor-Critic: Off-Policy Reinforcement Learning for Addressing Value Estimation Errors
Jingliang Duan, Yang Guan, Shengbo Eben Li +2
In reinforcement learning (RL), function approximation errors are known to easily lead to the Q-value overestimations, thus greatly reducing policy performance. This paper presents…