Open-ended Learning Leads To Generally Capable Agents

Abstract

In this work we create agents that can perform well beyond a single, individual task, that exhibit much wider generalisation of behaviour to a massive, rich space of challenges. We define a universe of tasks within an environment domain and demonstrate the ability to train agents that are generally capable across this vast space and beyond. The environment is natively multi-agent, spanning the continuum of competitive, cooperative, and independent games, which are situated within procedurally generated physical 3D worlds. The resulting space is exceptionally diverse in terms of the challenges posed to agents, and as such, even measuring the learning progress of an agent is an open research problem. We propose an iterative notion of improvement between successive generations of agents, rather than seeking to maximise a singular objective, allowing us to quantify progress despite tasks being incomparable in terms of achievable rewards. We show that through constructing an open-ended lear

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyopenendedlearningteam2021open

Related papers

• Robust Agents In Open-ended Worlds (2025)0.00
• An Efficient Open World Environment For Multi-agent Social Learning (2025)0.00
• A Definition Of Open-ended Learning Problems For Goal-conditioned Agents (2023)0.00
• Augmentative Topology Agents For Open-ended Learning (2022)2.26
• Emergence Of Collective Open-ended Exploration From Decentralized Meta-reinforcement Learning (2023)0.00
• MAESTRO: Open-ended Environment Design For Multi-agent Reinforcement Learning (2023)0.00
• Developing, Evaluating And Scaling Learning Agents In Multi-agent Environments (2022)2.26
• Learning Curricula In Open-ended Worlds (2023)0.00