18 citations · 45 across the 20 of their papers we have counts for
21 papers
Graph-Operator World Models for Morphology-Parameter Generalization in Continuous Control
Xu Yang, Yiqin Yang, Qianchuan Zhao
World models for continuous control are commonly trained for a fixed physical system and can degrade when known morphology parameters such as link lengths, masses, damping, and act…
Multi-Agent Reinforcement Learning via Agent-Specific Preference
Ni Mu, Yao Luan, Yiqin Yang +1
Multi-agent reinforcement learning (MARL) is a powerful framework for solving complex collaborative tasks, but it relies heavily on well-defined global reward functions. Designing…
Sim2O: Efficient Offline-to-Online MARL via Joint Action Composition
Bingchang Song, Yiqin Yang
Offline-to-online adaptation serves as a pivotal paradigm for mitigating the prohibitive cost of online exploration by bootstrapping reinforcement learning from offline datasets. W…
Curriculum reinforcement learning with measurable task representation learning
Yongyan Wen, Siyuan Li, Mingjian Fu +3
In curriculum reinforcement learning (CRL), an agent incrementally accumulates knowledge over a sequence of tasks (i.e., a curriculum), and the learning process is aimed at using t…
OPRIDE: Offline Preference-based Reinforcement Learning via In-Dataset Exploration
Yiqin Yang, Hao Hu, Yihuan Mao +10
Preference-based reinforcement learning (PbRL) can help avoid sophisticated reward designs and align better with human intentions, showing great promise in various real-world appli…
Data-Enabled Policy and Value Iteration for Continuous-Time Linear Quadratic Output Feedback Control
Jun Xie, Yuan-Hua Ni, Yiqin Yang +1
This paper proposes efficient policy iteration and value iteration algorithms for the continuous-time linear quadratic regulator problem with unmeasurable states and unknown system…
DAIL: Beyond Task Ambiguity for Language-Conditioned Reinforcement Learning
Runpeng Xie, Quanwei Wang, Hao Hu +7
Comprehending natural language and following human instructions are critical capabilities for intelligent agents. However, the flexibility of linguistic instructions induces substa…
CLARIFY: Contrastive Preference Reinforcement Learning for Untangling Ambiguous Queries
Ni Mu, Hao Hu, Xiao Hu +3
Preference-based reinforcement learning (PbRL) bypasses explicit reward engineering by inferring reward functions from human preference comparisons, enabling better alignment with…
Fewer May Be Better: Enhancing Offline Reinforcement Learning with Reduced Dataset
Yiqin Yang, Quanwei Wang, Chenghao Li +8
Offline reinforcement learning (RL) represents a significant shift in RL research, allowing agents to learn from pre-collected datasets without further interaction with the environ…
Episodic Novelty Through Temporal Distance
Yuhua Jiang, Qihan Liu, Yiqin Yang +8
Exploration in sparse reward environments remains a significant challenge in reinforcement learning, particularly in Contextual Markov Decision Processes (CMDPs), where environment…
S-EPOA: Overcoming the Indistinguishability of Segments with Skill-Driven Preference-Based Reinforcement Learning
Ni Mu, Yao Luan, Yiqin Yang +2
Preference-based reinforcement learning (PbRL) stands out by utilizing human preferences as a direct reward signal, eliminating the need for intricate reward engineering. However,…
Bayesian Design Principles for Offline-to-Online Reinforcement Learning
Hao Hu, Yiqin Yang, Jianing Ye +7
Offline reinforcement learning (RL) is crucial for real-world applications where exploration can be costly or unsafe. However, offline learned policies are often suboptimal, and fu…
No Prior Mask: Eliminate Redundant Action for Deep Reinforcement Learning
Dianyu Zhong, Yiqin Yang, Qianchuan Zhao
The large action space is one fundamental obstacle to deploying Reinforcement Learning methods in the real world. The numerous redundant actions will cause the agents to make repea…
Unsupervised Behavior Extraction via Random Intent Priors
Hao Hu, Yiqin Yang, Jianing Ye +2
Reward-free data is abundant and contains rich prior knowledge of human behaviors, but it is not well exploited by offline reinforcement learning (RL) algorithms. In this paper, we…
Learning Diverse Risk Preferences in Population-based Self-play
Yuhua Jiang, Qihan Liu, Xiaoteng Ma +5
Among the great successes of Reinforcement Learning (RL), self-play algorithms play an essential role in solving competitive games. Current self-play algorithms optimize the agent…
The Provable Benefits of Unsupervised Data Sharing for Offline Reinforcement Learning
Hao Hu, Yiqin Yang, Qianchuan Zhao +1
Self-supervised methods have become crucial for advancing deep learning by leveraging data itself to reduce the need for expensive annotations. However, the question of how to cond…
Flow to Control: Offline Reinforcement Learning with Lossless Primitive Discovery
Yiqin Yang, Hao Hu, Wenzhe Li +4
Offline reinforcement learning (RL) enables the agent to effectively learn from logged data, which significantly extends the applicability of RL algorithms in real-world scenarios…
On the Role of Discount Factor in Offline Reinforcement Learning
Hao Hu, Yiqin Yang, Qianchuan Zhao +1
Offline reinforcement learning (RL) enables effective learning from previously collected data without exploration, which shows great promise in real-world applications when explora…
Offline Reinforcement Learning with Value-based Episodic Memory
Xiaoteng Ma, Yiqin Yang, Hao Hu +5
Offline reinforcement learning (RL) shows promise of applying RL to real-world problems by effectively utilizing previously collected data. Most existing offline RL algorithms use…
Believe What You See: Implicit Constraint Approach for Offline Multi-Agent Reinforcement Learning
Yiqin Yang, Xiaoteng Ma, Chenghao Li +5
Learning from datasets without interaction with environments (Offline Learning) is an essential step to apply Reinforcement Learning (RL) algorithms in real-world scenarios. Howeve…
Modeling the Interaction between Agents in Cooperative Multi-Agent Reinforcement Learning
Xiaoteng Ma, Yiqin Yang, Chenghao Li +3
Value-based methods of multi-agent reinforcement learning (MARL), especially the value decomposition methods, have been demonstrated on a range of challenging cooperative tasks. Ho…