← Back to all news
arXiv AI By Xinyu Qiao, Yudong Hu, Congying Han, Weiyan Wu, Tiande Guo

Preference-based opponent shaping in differentiable games

Read the original on arXiv AI →

The paper introduces Preference-based Opponent Shaping (PBOS), a method that incorporates a preference parameter into an agent’s loss function to directly consider an opponent’s loss during strategy updates. By jointly learning strategy and preference parameters, PBOS aims to guide agents toward cooperative or competitive behaviors without relying on simple opponent predictions. Experiments on differentiable games demonstrate that PBOS enables agents to achieve better reward distributions across various environments.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Jul 7

Integrated Altruistic and Fairness Preference Induces Advanced Mutual Cooperation in Sequential Social Dilemmas

arXiv:2607. 04710v1 Announce Type: new Abstract: Inducing cooperation among distributed agents is still a difficult problem in the field of multi-agent reinforcement learning (MARL), particularly in social dilemma situations.

By Yu Wei, Yukiko Ogura, Yoshiyuki Ohmura, Ildefons Magrans de Abril, Hoshinori Kanazawa, Yasuo Kuniyoshi
agentsreinforcement-learningsafety
More like this →
arXiv Machine Learning
Sep 11

UBCL: A Reinforcement Learning Framework for Controllable and Diverse Player Behaviors

The paper presents UBCL, a reinforcement learning framework that generates controllable and diverse player behaviors without using human gameplay data. By defining behavior in an N‑dimensional continuous space and training a single PPO‑based multi‑agent policy with target behavior vectors, the method learns how actions affect behavioral statistics such as aggressiveness, mobility, and cooperativeness. Experiments in a custom Unity multiplayer game demonstrate that UBCL achieves greater behavioral diversity than a win‑only baseline and accurately matches specified behavior vectors across a range of targets.

By Atahan Cilan, Atay \"Ozg\"ovde
agentsreinforcement-learning
More like this →
arXiv AI
Sep 18

Mitigating Retaliatory Algorithmic Collusion in Repeated Games

The paper introduces CURB, a reward‑shaping framework that penalizes the total variation distance between an agent’s action distributions under cooperation and defection histories, thereby preventing collusive equilibria in repeated games. By linking empirical Q‑learning collusion to Simple Penal Codes, the authors prove that any non‑trivial SPC can be neutralized, and demonstrate CURB’s effectiveness in both tabular and deep Q‑learning settings for Bertrand and Cournot competition.

By Karthik Sivachandran, Rohan Paleja
agentsreinforcement-learning
More like this →