paper-with-me

홈 › Papers

ColorGrid: A Multi-Agent Non-Stationary Environment for Goal Inference and Assistance

2025-01-17 · Andrey Risukhin, Kavel Rao, Ben Caffee, Alan Fan

Autonomous agents' interactions with humans are increasingly focused on adapting to their changing preferences in order to improve assistance in real-world tasks. Effective agents must learn to accurately infer human goals, which are often hidden, to collaborate well. However, existing Multi-Agent Reinforcement Learning (MARL) environments lack the necessary attributes required to rigorously evaluate these agents' learning capabilities. To this end, we introduce ColorGrid, a novel MARL environment with customizable non-stationarity, asymmetry, and reward structure. We investigate the performance of Independent Proximal Policy Optimization (IPPO), a state-of-the-art (SOTA) MARL algorithm, in ColorGrid and find through extensive ablations that, particularly with simultaneous non-stationary and asymmetric goals between a `leader'' agent representing a human and a `follower'' assistant agent, ColorGrid is unsolved by IPPO. To support benchmarking future MARL algorithms, we release our environment code, model checkpoints, and trajectory visualizations at https://github.com/andreyrisukhin/ColorGrid.

📄 PDF Abstract BibTeX arXiv:2501.10593

Code (1)

andreyrisukhin/colorgrid 공식 구현 pytorch

Tasks

BenchmarkingMulti-agent Reinforcement Learning

Similar Papers 제목 키워드 기반

Causal Knowledge Transfer for Multi-Agent Reinforcement Learning in Dynamic Environments

2025-07-18 · Kathrin Korte, Christian Medeiros Adriano, Sona Ghahremani, Holger Giese arxiv

[Context] Multi-agent reinforcement learning (MARL) has achieved notable success in environments where agents must learn coordinated behaviors. However, transferring knowledge across agents remains challenging in non-sta…

Multi-agent Reinforcement Learning

Open-World Multi-Task Control Through Goal-Aware Representation Learning and Adaptive Horizon Prediction

2023-01-21 · CVPR 2023 1 · Shaofei Cai, ZiHao Wang, Xiaojian Ma, Anji Liu 외

We study the problem of learning goal-conditioned policies in Minecraft, a popular, widely accessible yet challenging open-ended environment for developing human-level multi-task agents. We first identify two main challe…

DiversityMinecraftRepresentation LearningZero-shot Generalization

Distributed Online Life-Long Learning (DOL3) for Multi-agent Trust and Reputation Assessment in E-commerce

2024-10-21 · Hariprasauth Ramamoorthy, Shubhankar Gupta, Suresh Sundaram

Trust and Reputation Assessment of service providers in citizen-focused environments like e-commerce is vital to maintain the integrity of the interactions among agents. The goals and objectives of both the service provi…

Agent Probing Interaction Policies

2019-11-21 · Siddharth Ghiya, Oluwafemi Azeez, Brendan Miller

Reinforcement learning in a multi agent system is difficult because these systems are inherently non-stationary in nature. In such a case, identifying the type of the opposite agent is crucial and can help us address thi…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

A Hybrid, PDE-ODE Control Strategy for Intercepting an Intelligent, well-informed Target in a Stationary, Cluttered Environment

2016-08-20 · Ahmad A. Masoud

In [1,2] a new class of intelligent controllers that can semantically embed an agent in a spatial context constraining its behavior in a goal-oriented manner was suggested. A controller of such a class can guide an agent…