 -DQN: Improving Deep Q-Learning By Evolving the BehaviorAdaptive Agents and Multi-Agent Systems (AAMAS), 2025 |
 RAT: Adversarial Attacks on Deep Reinforcement Agents for Targeted
BehaviorsAAAI Conference on Artificial Intelligence (AAAI), 2024 |
 Utilize the Flow before Stepping into the Same River Twice: Certainty
Represented Knowledge Flow for Refusal-Aware Instruction TuningAAAI Conference on Artificial Intelligence (AAAI), 2024 |
 PEARL: Zero-shot Cross-task Preference Alignment and Robust Reward
Learning for Robotic ManipulationInternational Conference on Machine Learning (ICML), 2023 |
 robosuite: A Modular Simulation Framework and Benchmark for Robot Learning Yuke Zhu J. Wong Ajay Mandlekar Roberto Martín-Martín Abhishek Joshi Soroush Nasiriany Yifeng Zhu Soroush Nasiriany Yifeng Zhu |
