6 papers
Language-Critique Imitation Learning from Suboptimal Demonstrations
Chih-Han Yang, Dai-Jie Wu, Yun-Ping Huang +3
Prior work on imitation learning from suboptimal demonstrations typically relies on compressed supervision signals such as confidence estimates, discriminator scores, or importance…
Policy Split: Incentivizing Dual-Mode Exploration in LLM Reinforcement with Dual-Mode Entropy Regularization
Jiashu Yao, Heyan Huang, Daiqing Wu +2
To encourage diverse exploration in reinforcement learning (RL) for large language models (LLMs) without compromising accuracy, we propose Policy Split, a novel paradigm that bifur…
SAD-Flower: Flow Matching for Safe, Admissible, and Dynamically Consistent Planning
Tzu-Yuan Huang, Armin Lederer, Dai-Jie Wu +6
Flow matching (FM) has shown promising results in data-driven planning. However, it inherently lacks formal guarantees for ensuring state and action constraints, whose satisfaction…
CooT: Learning to Coordinate In-Context with Coordination Transformers
Huai-Chih Wang, Hsiang-Chun Chuang, Hsi-Chun Cheng +2
Effective coordination among unfamiliar partners remains a major challenge in multi-agent systems. Existing approaches, such as population-based methods, improve robustness through…
Diffusion Imitation from Observation
Bo-Ruei Huang, Chun-Kai Yang, Chun-Mao Lai +2
Learning from observation (LfO) aims to imitate experts by learning from state-only demonstrations without requiring action labels. Existing adversarial imitation learning approach…
CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents
Tianqi Xu, Linyao Chen, Dai-Jie Wu +13
The development of autonomous agents increasingly relies on Multimodal Language Models (MLMs) to perform tasks described in natural language with GUI environments, such as websites…