To achieve autonomy in a priori unknown real-world scenarios, agents should be able to: i) act from high-dimensional sensory observations (e.g., images), ii) learn from past experience to adapt and improve, and iii) be capable of long horizon planning.

Toaddressthis, we need simple'normative' assumptions, which cannot be deduced exclusively fromobservations.

This creates a tight feedback loop between representation learning,memory,reinforcementlearning,andsampling-basedplanning.

We demonstrate the algorithm's effectiveness

Planning enables autonomous agents to solve complex decision-making problems by evaluating predictions of the future. However, classical planning algorithms often become infeasible in real-world settings where state spaces are high-dimensional andtransitiondynamicsunknown.