3 citations · 8 across the 8 of their papers we have counts for
9 papers
Demonstration-Free Success-Probability Reward Learning for Generalist Robot Policies
Duo Wu, Haifeng Wang, Rongwei Lu +6
Reinforcement learning (RL) enables generalist robot policies to improve through trial-and-error interaction, yet its effectiveness is fundamentally constrained by sparse task rewa…
Heterogeneous Agent Collaborative Reinforcement Learning
Zhixia Zhang, Zixuan Huang, Gongxun Li +10
We introduce Heterogeneous Agent Collaborative Reinforcement Learning (HACRL), a new Reinforcement Learning from Verifiable Reward (RLVR) problem that addresses the inefficiencies…
Mean-Semivariance Policy Optimization via Risk-Averse Reinforcement Learning
Xiaoteng Ma, Shuai Ma, Li Xia +1
Keeping risk under control is often more crucial than maximizing expected rewards in real-world decision-making situations, such as finance, robotics, autonomous driving, etc. The…
A unified algorithm framework for mean-variance optimization in discounted Markov decision processes
Shuai Ma, Xiaoteng Ma, Li Xia
This paper studies the risk-averse mean-variance optimization in infinite-horizon discounted Markov decision processes (MDPs). The involved variance metric concerns reward variabil…
First- and Second-Moment Constrained Gaussian Channels
Shuai Ma, Michèle Wigger
This paper studies the channel capacity of intensity-modulation direct-detection (IM/DD) visible light communication (VLC) systems under both optical and electrical power constrain…
Variance-Based Risk Estimations in Markov Processes via Transformation with State Lumping
Shuai Ma, Jia Yuan Yu
Variance plays a crucial role in risk-sensitive reinforcement learning, and most risk measures can be analyzed via variance. In this paper, we consider two law-invariant risks as e…
A Scheme for Dynamic Risk-Sensitive Sequential Decision Making
Shuai Ma, Jia Yuan Yu, Ahmet Satir
We present a scheme for sequential decision making with a risk-sensitive objective and constraints in a dynamic environment. A neural network is trained as an approximator of the m…
State-Augmentation Transformations for Risk-Sensitive Reinforcement Learning
Shuai Ma, Jia Yuan Yu
In the framework of MDP, although the general reward function takes three arguments-current state, action, and successor state; it is often simplified to a function of two argument…
Transition-based versus State-based Reward Functions for MDPs with Value-at-Risk
Shuai Ma, Jia Yuan Yu
In reinforcement learning, the reward function on current state and action is widely used. When the objective is about the expectation of the (discounted) total reward only, it wor…