Related papers: Truthful Self-Play
As AI agents become increasingly capable of tool use and long-horizon tasks, they have begun to be deployed in settings where multiple agents can interact. However, whereas prior work has mostly focused on human-AI interactions, there is an…
In this work, we develop a reinforcement learning protocol for a multiagent coordination task in a discrete state and action space: an iterated prisoner's dilemma game extended into a team based, winner-take all tournament, which forces the…
Recent advances in large language model (LLM) reasoning, led by reinforcement learning with verifiable rewards (RLVR), have inspired self-play post-training, where models improve by generating and solving their own problems. While self-play…
Replay is a powerful strategy to promote learning in artificial intelligence and the brain. However, the conditions to generate it and its functional advantages have not been fully recognized. In this study, we develop a modular…
Traffic scenarios are inherently interactive. Multiple decision-makers predict the actions of others and choose strategies that maximize their rewards. We view these interactions from the perspective of game theory which introduces various…
Large and diverse datasets have been the cornerstones of many impressive advancements in artificial intelligence. Intelligent creatures, however, learn by interacting with the environment, which changes the input sensory signals and the…
Making sophisticated, robust, and safe sequential decisions is at the heart of intelligent systems. This is especially critical for planning in complex multi-agent environments, where agents need to anticipate other agents' intentions and…
Learning meaningful representations that maintain the content necessary for a particular task while filtering away detrimental variations is a problem of great interest in machine learning. In this paper, we tackle the problem of learning…
Traditionally, reinforcement learning methods predict the next action based on the current state. However, in many situations, directly applying actions to control systems or robots is dangerous and may lead to unexpected behaviors because…
Reward function, as an incentive representation that recognizes humans' agency and rationalizes humans' actions, is particularly appealing for modeling human behavior in human-robot interaction. Inverse Reinforcement Learning is an…
When developing reinforcement learning agents, the standard approach is to train an agent to converge to a fixed policy that is as close to optimal as possible for a single fixed reward function. If different agent behaviour is required in…
Evolutionary game theory predicts that cooperation in social dilemma games is promoted when agents are connected as a network. However, when networks are fixed over time, humans do not necessarily show enhanced mutual cooperation. Here we…
Model-free reinforcement learning (RL) requires a large number of trials to learn a good policy, especially in environments with sparse rewards. We explore a method to improve the sample efficiency when we have access to demonstrations. Our…
Asymmetrical multiplayer (AMP) game is a popular game genre which involves multiple types of agents competing or collaborating with each other in the game. It is difficult to train powerful agents that can defeat top human players in AMP…
Peer-To-Peer (P2P) networks are self-organizing, distributed systems, with no centralized authority or infrastructure. Because of the voluntary participation, the availability of resources in a P2P system can be highly variable and…
Optimization of parameterized policies for reinforcement learning (RL) is an important and challenging problem in artificial intelligence. Among the most common approaches are algorithms based on gradient ascent of a score function…
In this paper, we study inverse game theory (resp. inverse multiagent learning) in which the goal is to find parameters of a game's payoff functions for which the expected (resp. sampled) behavior is an equilibrium. We formulate these…
Pommerman is a multi-agent environment that has received considerable attention from researchers in recent years. This environment is an ideal benchmark for multi-agent training, providing a battleground for two teams with communication…
We study interpersonal trust by means of the all-or-nothing public goods game between agents on a network. The agents are endowed with the simple yet adaptive learning rule, exponential moving average, by which they estimate the behavior of…
A simple model for cooperation between "selfish" agents, which play an extended version of the Prisoner's Dilemma(PD) game, in which they use arbitrary payoffs, is presented and studied. A continuous variable, representing the probability…