marginaliaA PODCASTExplore all episodes

AI & Computer Science · Weekly AI Papers

PlaNet: Learning Latent Dynamics for Planning from Pixels (Danijar Hafner et al.)

LISTEN TO THIS EPISODE

Source cover or paper first page: Learning Latent Dynamics for Planning from Pixels

Danijar Hafner and colleagues introduce PlaNet, an agent that learns dynamics from images and plans in latent space.

Its recurrent state-space model combines deterministic memory with stochastic states.

Planning compares predicted action sequences before acting and updating from new observations.

The paper studies latent overshooting and evaluates control across six simulated tasks.

The discussion examines sample efficiency, model uncertainty, and the limits of planning with learned predictions.

Technical clarification: CEM samples a Gaussian distribution, which is not uniform over actions. The variational objective bounds log evidence and includes reconstruction, reward prediction, and KL terms; KL divergence compares distributions rather than literally stretching bell curves. The six-task experiment establishes neither zero-shot transfer nor inevitable failure on every unseen task.

Listen on the podcast website

Read about the original source: Learning Latent Dynamics for Planning from Pixels

Part of Marginalia: books, papers, and ideas for learning and debate.