Robust Agents In Open-ended Worlds

Abstract

The growing prevalence of artificial intelligence (AI) in various applications underscores the need for agents that can successfully navigate and adapt to an ever-changing, open-ended world. A key challenge is ensuring these AI agents are robust, excelling not only in familiar settings observed during training but also effectively generalising to previously unseen and varied scenarios. In this thesis, we harness methodologies from open-endedness and multi-agent learning to train and evaluate robust AI agents capable of generalising to novel environments, out-of-distribution inputs, and interactions with other co-player agents. We begin by introducing MiniHack, a sandbox framework for creating diverse environments through procedural content generation. Based on the game of NetHack, MiniHack enables the construction of new tasks for reinforcement learning (RL) agents with a focus on generalisation. We then present Maestro, a novel approach for generating adversarial curricula that progre

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keysamvelyan2025robust

Related papers

• Open-ended Learning Leads To Generally Capable Agents (2021)0.00
• An Efficient Open World Environment For Multi-agent Social Learning (2025)0.00
• Hackatari: Atari Learning Environments For Robust And Continual Reinforcement Learning (2024)0.00
• MAESTRO: Open-ended Environment Design For Multi-agent Reinforcement Learning (2023)0.00
• Learning Curricula In Open-ended Worlds (2023)0.00
• The AI Arena: A Framework For Distributed Multi-agent Reinforcement Learning (2021)0.00
• Augmentative Topology Agents For Open-ended Learning (2022)2.26
• Winning Isn't Everything: Enhancing Game Development With Intelligent Agents (2019)11.29