Learning Latent Dynamics for Planning from Pixels

Authors:
  • DHDanijar Hafner
    Danijar Hafner
  • TLTimothy Lillicrap
    Timothy Lillicrap
  • IFIan Fischer
    Ian Fischer
  • RVRuben Villegas
    Ruben Villegas
  • DHDavid Ha
    David Ha
  • HLHonglak Lee
    Honglak Lee
  • JDJames Davidson
    James Davidson
Preprint
Publisher website
Google Scholar
Abstract
Planning has been very successful for control tasks with known environment dynamics. To leverage planning in unknown environments, the agent needs to learn the dynamics from interactions with the world. However, learning dynamics models that are accurate enough for planning has been a long-standing challenge, especially in image-based domains. We propose the Deep Planning Network (PlaNet), a purely model-based agent that learns the environment dynamics from images and chooses actions through fast online planning in latent space. To achieve high performance, the dynamics model must accurately predict the rewards ahead for multiple time steps. We approach this using a latent dynamics model with both deterministic and stochastic transition components. Moreover, we propose a multi-step variational inference objective that we name latent overshooting. Using only pixel observations, our agent solves continuous control tasks with contact dynamics, partial observability, and sparse rewards, which exceed the difficulty of tasks that were previously solved by planning with learned models. PlaNet uses substantially fewer episodes and reaches final performance close to and sometimes higher than strong model-free algorithms.

This publication has 8 references indexed in Scilit: