← Authors

Xiaoteng Ma

17 papers · 2021–2025 · 5 conferences · across top CS/AI conferences

Achievements

πŸ—ΊοΈ Taxonomy Completionist (13) 🌍 Conference Polyglot (5) 🐝 Cross-Pollinator (8) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird πŸŒ‰ Interdisciplinary Bridge πŸ† Keyword Champion (3) πŸ‘‘ Triple Crown πŸ† Grand Slam πŸ”₯ Unstoppable (5) πŸ’Ž Century Club (17) ⚑ Prolific Year (5) ❓ The Questioner

Conferences

NIPS (6) ICLR (5) AAAI (2) ICML (2) IJCAI (2)

Top co-authors

Jun Yang (8) Qianchuan Zhao (6) Qihan Liu (5) Bin Liang (5) Chongjie Zhang (5) Jiafei Lyu (4) Xiu Li (4) Yiqin Yang (4) Yuhua Jiang (3) Rui Yang (3)

Keywords

offline reinforcement learning (4) value estimation (3) continuous control (2) deep reinforcement learning (2) value function (2) distribution shift (2) reinforcement learning (2) policy optimization (2) ood generalization (1) competitive game (1) domain generalization (1) dynamics mismatch (1) out-of-distribution action (1) reward shaping (1) extrapolation error (1) trust region (1) policy gradient (1) policy transfer (1) adversarial robustness (1) sample efficiency (1)

Papers

Episodic Novelty Through Temporal Distance ICLR 2025
Cross-Domain Offline Policy Adaptation with Optimal Transport and Dataset Constraint ICLR 2025
Efficient Multi-agent Reinforcement Learning by Planning ICLR 2024
NeuralPlane: An Efficiently Parallelizable Platform for Fixed-wing Aircraft Control with Reinforcement Learning NIPS 2024
Learning Diverse Risk Preferences in Population-Based Self-Play AAAI 2024
SEABO: A Simple Search-Based Method for Offline Imitation Learning ICLR 2024
Single-Trajectory Distributionally Robust Reinforcement Learning ICML 2024
What is Essential for Unseen Goal Generalization of Offline Goal-conditioned RL? ICML 2023
Cross-Domain Policy Adaptation via Value-Guided Data Filtering NIPS 2023
Mean-Semivariance Policy Optimization via Risk-Averse Reinforcement Learning (Extended Abstract) IJCAI 2023
Offline Reinforcement Learning with Value-based Episodic Memory ICLR 2022
Mildly Conservative Q-Learning for Offline Reinforcement Learning NIPS 2022
RORL: Robust Offline Reinforcement Learning via Conservative Smoothing NIPS 2022
Exploit Reward Shifting in Value-Based Deep-RL: Optimistic Curiosity-Based Exploration and Conservative Exploitation via Linear Reward Shaping NIPS 2022
Efficient Continuous Control with Double Actors and Regularized Critics AAAI 2022
Average-Reward Reinforcement Learning with Trust Region Methods IJCAI 2021
Believe What You See: Implicit Constraint Approach for Offline Multi-Agent Reinforcement Learning NIPS 2021