Learning General World Models in a Handful of Reward-Free Deployments

October 25, 2022


Building generally capable agents is a grand challenge for deep reinforcement learning (RL). To approach this challenge practically, we outline two key desiderata: 1) to facilitate generalization, exploration should be task agnostic; 2) to facilitate scalability, exploration policies should collect large quantities of data without costly centralized retraining. Combining these two properties, we introduce the reward-free deployment efficiency setting, a new paradigm for RL research. We then present CASCADE, a novel approach for self-supervised exploration in this new setting. CASCADE seeks to learn a world model by collecting data with a population of agents, using an information theoretic objective inspired by Bayesian Active Learning. CASCADE achieves this by specifically maximizing the diversity of trajectories sampled by the population through a novel cascading objective. We provide theoretical intuition for CASCADE which we show in a tabular setting improves upon naïve approaches that do not account for population diversity. We then demonstrate that CASCADE collects diverse task-agnostic datasets and learns agents that generalize zero-shot to novel, unseen downstream tasks on Atari, MiniGrid, Crafter and the DM Control Suite. Code and videos are available at

Download the Paper


Written by

Yingchen Xu

Aldo Pacchiano

Edward Grefenstette

Jack Parker-Holder

Oleh Rybkin

Philip J. Ball

Stephen Roberts

Tim Rockstäschel



Research Topics

Reinforcement Learning

Related Publications

November 28, 2022



Neural Attentive Circuits

Nicolas Ballas, Bernhard Schölkopf, Chris Pal, Francesco Locatello, Li Erran, Martin Weiss, Nasim Rahaman, Yoshua Bengio

November 28, 2022

November 27, 2022


Near Instance-Optimal PAC Reinforcement Learning for Deterministic MDPs

Andrea Tirinzoni, Aymen Al Marjani, Emilie Kaufmann

November 27, 2022

November 16, 2022



Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Models

Kushal Tirumala, Aram H. Markosyan, Armen Aghajanyan, Luke Zettlemoyer

November 16, 2022

November 10, 2022



Learning State-Aware Visual Representations from Audible Interactions

Unnat Jain, Abhinav Gupta, Himangi Mittal, Pedro Morgado

November 10, 2022

Help Us Pioneer The Future of AI

We share our open source frameworks, tools, libraries, and models for everything from research exploration to large-scale production deployment.