Generally capable agents emerge from open-ended play
WEBJul 27, 2021 · We created a vast game environment we call XLand, which includes many multiplayer games within consistent, human-relatable 3D worlds. This environment makes it possible to formulate new learning algorithms, which dynamically control how an agent trains and the games on which it trains.
Title: Open-Ended Learning Leads to Generally Capable Agents
WEBJul 27, 2021 · Open-Ended Learning Leads to Generally Capable Agents. 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.
Human-Timescale Adaptation - Google Sites
WEBWe train our agent in XLand, a vast, smooth and diverse task space of adaptation problems. Different tasks have different adaptation requirements, such as experimentation, tool use or division of...
An endlessly changing playground teaches AIs how to multitask
WEBJul 30, 2021 · DeepMind has developed a vast candy-colored virtual playground that teaches AIs general skills by endlessly changing the tasks it sets them. Instead of developing just the skills needed to solve...
Is DeepMind’s new reinforcement learning system a step toward …
WEBAug 2, 2021 · The goal of DeepMind’s new project was to create “an artificial agent whose behaviour generalises beyond the set of games it was trained on.” To this end, the team created XLand, an engine that can generate 3D environments composed of static topology and moveable objects.
DeepMind’s Vibrant New Virtual World Trains ... - Singularity Hub
WEBAug 1, 2021 · The paper’s authors said they’ve created an endlessly challenging virtual playground for AI. The world, called XLand, is a vibrant video game managed by an AI overlord and populated by algorithms that must learn the skills to navigate it.
GitHub - corl-team/xland-minigrid: JAX-accelerated Meta …
WEBXLand-MiniGrid is a suite of tools, grid-world environments and benchmarks for meta-reinforcement learning research inspired by the diversity and depth of XLand and the simplicity and minimalism of MiniGrid.
DeepMind Introduces XLand: An Open-Ended 3D Simulated ... - MarkTechPost
WEBAug 4, 2021 · To address this issue, DeepMind researchers set out an aim to create a robust artificial agent whose behavior generalizes beyond the training set of games. For this, they introduce an open-ended 3D simulated environment space for training and evaluating artificial agents.
DeepMind Trains AI Agent in a New Dynamic and Interactive XLand
WEBJul 30, 2021 · DeepMind's New XLand trains AI agents to play Capture the Flag, Hide and Seek, or Catch even though they have never seen those games.
arXiv.org e-Print archive
WEBarXiv.org e-Print archive
- Some results have been removed