Portrait de Arjun Vaithilingam Sudhakar n'est pas disponible

Arjun Vaithilingam Sudhakar

Doctorat - Polytechnique
Superviseur⋅e principal⋅e
Sarath Chandar
Sujets de recherche
Apprentissage par renforcement
Traitement du langage naturel

Publications

A Generalist Hanabi Agent
Arjun Vaithilingam Sudhakar
Hadi Nekoei
Mathieu Reymond
Miao Liu
Janarthanan Rajendran
Sarath Chandar
Traditional multi-agent reinforcement learning (MARL) systems can develop cooperative strategies through repeated interactions. However, the… (voir plus)se systems are unable to perform well on any other setting than the one they have been trained on, and struggle to successfully cooperate with unfamiliar collaborators. This is particularly visible in the Hanabi benchmark, a popular 2-to-5 player cooperative card-game which requires complex reasoning and precise assistance to other agents. Current MARL agents for Hanabi can only learn one specific game-setting (e.g., 2-player games), and play with the same algorithmic agents. This is in stark contrast to humans, who can quickly adjust their strategies to work with unfamiliar partners or situations. In this paper, we introduce Recurrent Replay Relevance Distributed DQN (R3D2), a generalist agent for Hanabi, designed to overcome these limitations. We reformulate the task using text, as language has been shown to improve transfer. We then propose a distributed MARL algorithm that copes with the resulting dynamic observation- and action-space. In doing so, our agent is the first that can play all game settings concurrently, and extend strategies learned from one setting to other ones. As a consequence, our agent also demonstrates the ability to collaborate with different algorithmic agents -- agents that are themselves unable to do so. The implementation code is available at:
2025-01-21
ICLR.cc/2025/Conference (poster)
doi.org
openreview.net
Language Model-In-The-Loop: Data Optimal Approach to Learn-To-Recommend Actions in Text Games
Arjun Vaithilingam Sudhakar
Prasanna Parthasarathi
Janarthanan Rajendran
A. Chandar
2023-11-12
ArXiv (prépublication)
doi.org
arxiv.org