Related papers: Reinforcement learning with reputation-based adapt…

Feedback-evolving games is a framework that models the co-evolution between payoff functions and an environmental state. It serves as a useful tool to analyze many social dilemmas such as natural resource consumption, behaviors in…

With reinforcement learning, an agent could learn complex behaviors from high-level abstractions of the task. However, exploration and reward shaping remained challenging for existing methods, especially in scenarios where the extrinsic…

High-dimensional observations and complex real-world dynamics present major challenges in reinforcement learning for both function approximation and exploration. We address both of these challenges with two complementary techniques: First,…

The reinforcement learning paradigm allows, in principle, for complex behaviours to be learned directly from simple reward signals. In practice, however, it is common to carefully hand-design the reward function to encourage a particular…

Recent studies in the spatial prisoner's dilemma games with reinforcement learning have shown that static agents can learn to cooperate through a diverse sort of mechanisms, including noise injection, different types of learning algorithms…

We study reinforcement learning (RL) problems in which agents observe the reward or transition realizations at their current state before deciding which action to take. Such observations are available in many applications, including…

Real-world multi-agent scenarios often involve mixed motives, demanding altruistic agents capable of self-protection against potential exploitation. However, existing approaches often struggle to achieve both objectives. In this paper,…

In this paper, we propose a new solution to reward adaptation (RA) in reinforcement learning, where the agent adapts to a target reward function based on one or more existing source behaviors learned a priori under the same domain dynamics…

The universe involves many independent co-learning agents as an ever-evolving part of our observed environment. Yet, in practice, Multi-Agent Reinforcement Learning (MARL) applications are typically constrained to small, homogeneous…

The interplay between exploration and exploitation in competitive multi-agent learning is still far from being well understood. Motivated by this, we study smooth Q-learning, a prototypical learning model that explicitly captures the…

Human societies around the world interact with each other by developing and maintaining social norms, and it is critically important to understand how such norms emerge and change. In this work, we define an evolutionary game-theoretic…

This paper proposes an exploration technique for multi-agent reinforcement learning (MARL) with graph-based communication among agents. We assume the individual rewards received by the agents are independent of the actions by the other…

We study the evolution of behavior under reinforcement learning in a Prisoner's Dilemma where agents interact in a regular network and can learn about whether they play one-shot or repeatedly by incurring a cost of deliberation. With…

We study emergent social dynamics in LLM agents playing The Resistance: Avalon, a hidden-role deception game. Unlike prior work on single-game performance, our agents play repeated games while retaining memory of previous interactions,…

Model-based Reinforcement Learning approaches have the promise of being sample efficient. Much of the progress in learning dynamics models in RL has been made by learning models via supervised learning. But traditional model-based…

We study reinforcement learning from human feedback in general Markov decision processes, where agents learn from trajectory-level preference comparisons. A central challenge in this setting is to design algorithms that select informative…

Realistic environments often provide agents with very limited feedback. When the environment is initially unknown, the feedback, in the beginning, can be completely absent, and the agents may first choose to devote all their effort on…

As agentic AI becomes more widespread, agents with distinct and possibly conflicting goals will interact in complex ways. These multi-agent interactions pose a fundamental challenge, particularly in social dilemmas, where agents' individual…

Recent advances in reinforcement learning with social agents have allowed us to achieve human-level performance on some interaction tasks. However, most interactive scenarios do not have as end-goal performance alone; instead, the social…

We introduce exploration potential, a quantity that measures how much a reinforcement learning agent has explored its environment class. In contrast to information gain, exploration potential takes the problem's reward structure into…