Mastering Diverse Domains through World Models

Abstract

Developing a general algorithm that learns to solve tasks across a wide range of applications has been a fundamental challenge in artificial intelligence. Although current reinforcement learning algorithms can be readily applied to tasks similar to what they have been developed for, configuring them for new application domains requires significant human expertise and experimentation. We present DreamerV3, a general algorithm that outperforms specialized methods across over 150 diverse tasks, with a single configuration. Dreamer learns a model of the environment and improves its behavior by imagining future scenarios. Robustness techniques based on normalization, balancing, and transformations enable stable learning across domains. Applied out of the box, Dreamer is the first algorithm to collect diamonds in Minecraft from scratch without human data or curricula. This achievement has been posed as a significant challenge in artificial intelligence that requires exploring farsighted strategies from pixels and sparse rewards in an open world. Our work allows solving challenging control problems without extensive experimentation, making reinforcement learning broadly applicable.

Website: https://danijar.com/dreamerv3

Cited by in corpus (13)

• Harms from Increasingly Agentic Algorithmic Systems
• Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory
• Structure in Deep Reinforcement Learning: A Survey and Open Problems
• Barrier Functions Inspired Reward Shaping for Reinforcement Learning
• Multimodal Information Bottleneck for Deep Reinforcement Learning with Multiple Sensors
• Informed Reinforcement Learning for Situation-Aware Traffic Rule Exceptions
• On learning latent dynamics of the AUG plasma state
• Semi-supervised Multimodal Representation Learning through a Global Workspace
• Exploring the Potential of World Models for Anomaly Detection in Autonomous Driving
• Approximate Model-Based Shielding for Safe Reinforcement Learning
• Dual policy as self-model for planning
• Enhancing Reinforcement Learning Through Guided Search
• Mitigating Value Hallucination in Dyna Planning via Multistep Predecessor Models