Dream to Control: Learning Behaviors by Latent Imagination

by   Danijar Hafner, et al.

Learned world models summarize an agent's experience to facilitate learning complex behaviors. While learning world models from high-dimensional sensory inputs is becoming feasible through deep learning, there are many potential ways for deriving behaviors from them. We present Dreamer, a reinforcement learning agent that solves long-horizon tasks from images purely by latent imagination. We efficiently learn behaviors by propagating analytic gradients of learned state values back through trajectories imagined in the compact state space of a learned world model. On 20 challenging visual control tasks, Dreamer exceeds existing approaches in data-efficiency, computation time, and final performance.


page 2

page 5


Mastering Atari with Discrete World Models

Intelligent agents need to generalize from past experience to achieve go...

Steadily Learn to Drive with Virtual Memory

Reinforcement learning has shown great potential in developing high-leve...

LS3: Latent Space Safe Sets for Long-Horizon Visuomotor Control of Iterative Tasks

Reinforcement learning (RL) algorithms have shown impressive success in ...

Deep Latent Competition: Learning to Race Using Visual Control Policies in Latent Space

Learning competitive behaviors in multi-agent settings such as racing re...

Learning Composable Behavior Embeddings for Long-horizon Visual Navigation

Learning high-level navigation behaviors has important implications: it ...

Isolating and Leveraging Controllable and Noncontrollable Visual Dynamics in World Models

World models learn the consequences of actions in vision-based interacti...

Learning to Fly via Deep Model-Based Reinforcement Learning

Learning to control robots without requiring models has been a long-term...

Code Repositories


Dream to Control: Learning Behaviors by Latent Imagination

view repo