12 papers
RoboSynChallenge: Mastering Real-World Dexterity via Generalizing Synthesized Manipulation Skills
Runyi Zhao, Ruixin Wu, Chengkun Li +15
Achieving generalizable robotic manipulation remains a central challenge in embodied intelligence. Despite rapid advances in model architectures and learning algorithms, progress i…
ACPO: Agent-Chained Policy Optimization for Multi-Agent Reinforcement Learning
Daiki E. Matsunaga, Junho Na, Tri Wahyu Guntara +4
Cooperative tasks in Multi-Agent Reinforcement Learning (MARL) require agents to collectively maximize a shared return. Under the Centralized Training with Decentralized Execution…
Counterfactual Residual Data Augmentation for Regression
Hossein Mohebbi, Oliver Schulte, Ke Li +1
Data-driven modeling in real-world regression tasks often suffers from limited training samples, high collection costs, and noisy observations. Inspired by the impact of data augme…
Talk, Judge, Cooperate: Gossip-Driven Indirect Reciprocity in Self-Interested LLM Agents
Shuhui Zhu, Yue Lin, Shriya Kaistha +5
Indirect reciprocity, which means helping those who have helped others, is difficult to sustain among decentralized, self-interested LLM agents without reliable reputation systems.…
Policy-Conditioned Policies for Multi-Agent Task Solving
Yue Lin, Shuhui Zhu, Wenhao Li +5
In multi-agent tasks, the central challenge lies in the dynamic adaptation of strategies. However, directly conditioning on opponents' strategies is intractable in the prevalent de…
Image-POSER: Reflective RL for Multi-Expert Image Generation and Editing
Hossein Mohebbi, Mohammed Abdulrahman, Yanting Miao +2
Recent advances in text-to-image generation have produced strong single-shot models, yet no individual system reliably executes the long, compositional prompts typical of creative…
Information Bargaining: Bilateral Commitment in Bayesian Persuasion
Yue Lin, Shuhui Zhu, William A Cunningham +4
Bayesian persuasion, an extension of cheap-talk communication, involves an informed sender committing to a signaling scheme to influence a receiver's actions. Compared to cheap tal…
Measures of Variability for Risk-averse Policy Gradient
Yudong Luo, Yangchen Pan, Jiaqi Tan +1
Risk-averse reinforcement learning (RARL) is critical for decision-making under uncertainty, which is especially valuable in high-stake applications. However, most existing works f…
Learning to Negotiate via Voluntary Commitment
Shuhui Zhu, Baoxiang Wang, Sriram Ganapathi Subramanian +1
The partial alignment and conflict of autonomous agents lead to mixed-motive scenarios in many real-world applications. However, agents may fail to cooperate in practice even when…
A Comprehensive Survey on Inverse Constrained Reinforcement Learning: Definitions, Progress and Challenges
Guiliang Liu, Sheng Xu, Shicheng Liu +3
Inverse Constrained Reinforcement Learning (ICRL) is the task of inferring the implicit constraints that expert agents adhere to, based on their demonstration data. As an emerging…
Subject-driven Text-to-Image Generation via Preference-based Reinforcement Learning
Yanting Miao, William Loh, Suraj Kothawade +3
Text-to-image generative models have recently attracted considerable interest, enabling the synthesis of high-quality images from textual prompts. However, these models often lack…
Why Online Reinforcement Learning is Causal
Oliver Schulte, Pascal Poupart
Reinforcement learning (RL) and causal modelling naturally complement each other. The goal of causal modelling is to predict the effects of interventions in an environment, while t…