Related papers: Balancing of competitive two-player Game Levels wi…

We introduce a sampling perspective to tackle the challenging task of training robust Reinforcement Learning (RL) agents. Leveraging the powerful Stochastic Gradient Langevin Dynamics, we present a novel, scalable two-player RL algorithm,…

In fighting games, individual players of the same skill level often exhibit distinct strategies from one another through their gameplay. Despite this, the majority of AI agents for fighting games have only a single strategy for each "level"…

Recent progress in artificial intelligence through reinforcement learning (RL) has shown great success on increasingly complex single-agent environments and two-player turn-based games. However, the real-world contains multiple agents, each…

Cooperative Multi-Agent Reinforcement Learning (MARL) algorithms, trained only to optimize task reward, can lead to a concentration of power where the failure or adversarial intent of a single agent could decimate the reward of every agent…

Recent advancements in reinforcement learning have made significant impacts across various domains, yet they often struggle in complex multi-agent environments due to issues like algorithm instability, low sampling efficiency, and the…

The development of deep reinforcement learning (DRL) has benefited from the emergency of a variety type of game environments where new challenging problems are proposed and new algorithms can be tested safely and quickly, such as Board…

Many economic games and machine learning approaches can be cast as competitive optimization problems where multiple agents are minimizing their respective objective function, which depends on all agents' actions. While gradient descent is a…

Reinforcement learning has increasingly been applied to economic decision-making, including taxation, public spending, and labor supply. However, existing RL-based economic models typically consider only a single government-household group,…

We study what actually works and what doesn't for training large language models as agents via multi-turn reinforcement learning. Despite rapid progress, existing frameworks and definitions are fragmented, and there is no systematic…

This paper presents an adaptive level generation algorithm for the physics-based puzzle game Angry Birds. The proposed algorithm is based on a pre-existing level generator for this game, but where the difficulty of the generated levels can…

We study multi-task reinforcement learning (RL) in tabular episodic Markov decision processes (MDPs). We formulate a heterogeneous multi-player RL problem, in which a group of players concurrently face similar but not necessarily identical…

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…

Mean Field Control Games (MFCG), introduced in [Angiuli et al., 2022a], represent competitive games between a large number of large collaborative groups of agents in the infinite limit of number and size of groups. In this paper, we prove…

We present a computational framework for synthesis of distributed control strategies for a heterogeneous team of robots in a partially observable environment. The goal is to cooperatively satisfy specifications given as Truncated Linear…

Multi-agent reinforcement learning (MARL) has been gaining extensive attention from academia and industries in the past few decades. One of the fundamental problems in MARL is how to evaluate different approaches comprehensively. Most…

Learning in multi-agent scenarios is a fruitful research direction, but current approaches still show scalability problems in multiple games with general reward settings and different opponent types. The Multi-Agent Reinforcement Learning…

Two-stage Colonel Blotto game represents a typical adversarial resource allocation problem, in which two opposing agents sequentially allocate resources in a network topology across two phases: an initial resource deployment followed by…

Peer-to-peer (P2P) trading is increasingly recognized as a key mechanism for decentralized market regulation, yet existing approaches often lack robust frameworks to ensure fairness. This paper presents FairMarket-RL, a novel hybrid…

We present a new combined \textit{mean field control game} (MFCG) problem which can be interpreted as a competitive game between collaborating groups and its solution as a Nash equilibrium between groups. Players coordinate their strategies…

A central problem in the theory of multi-agent reinforcement learning (MARL) is to understand what structural conditions and algorithmic principles lead to sample-efficient learning guarantees, and how these considerations change as we move…