1

Off-Agent Trust Region Policy Optimization
Leveraging the experiences of other agents offers a powerful mechanism to enhance policy optimization in multi-agent reinforcement …
PDF Cite
ProgressGym: Alignment with a Millennium of Moral Progress
Frontier AI systems, including large language models (LLMs), hold increasing influence over the epistemology of human users. Such …
PDF Cite Code
Efficient Adaptation in Mixed-Motive Environments via Hierarchical Opponent Modeling and Planning
Despite the recent successes of multi-agent reinforcement learning (MARL) algorithms, efficiently adapting to co-players in …
PDF Cite
In-Context Editing: Learning Knowledge from Self-Induced Distributions
In scenarios where language models must incorporate new information efficiently without extensive retraining, traditional fine-tuning …
PDF Cite Code
Language models resist alignment: Evidence from data compression
Large language models (LLMs) may exhibit unintended or undesirable behaviors. Recent works have concentrated on aligning LLMs to …
PDF Cite Code DOI
Remember the Past for Better Future: Memory-Augmented Offline RL
As a foundation of human intelligence, memory has been found to be critical for human attention and decision making. However, it is …
Cite DOI
Anyskill: Learning Open-Vocabulary Physical Skill for Interactive Agents
Traditional approaches in physics-based motion generation centered around imitation learning and reward shaping often struggle to adapt …
PDF Cite
End-to-End Neuro-Symbolic Reinforcement Learning with Textual Explanations
Neuro-symbolic reinforcement learning (NS-RL) has emerged as a promising paradigm for explainable decision-making, characterized by the …
PDF Cite
A Perspective of Q-value Estimation on Offline-to-Online Reinforcement Learning
Offline-to-online Reinforcement Learning (O2O RL) aims to improve the performance of offline pretrained policy using only a few online …
Cite DOI
Grasp Multiple Objects with One Hand
The intricate kinematics of the human hand enable simultaneous grasping and manipulation of multiple objects, essential for tasks, such …
PDF Cite