# Deep Reinforcement Learning: Model Based Reinforcement Learning

** Published:**

Planning]; id1-->id3[Background

Planning]; id2-->id4[Continuous

Actions]; id2-->id5[Discrete

Actions]; id4-->id6[Shooting]; id4-->id7[Collocation]; id3-->id8[Simulate

Environment]; id3-->id9[Assist Learning

Algorithm]; id6-->id10[iLQR

DDP]:::methods; id7-->id11[Direct collocation

STOMP]:::methods; id5-->id12[Heuristic search

MCTS]:::methods; id8-->id13[DYNA

MVE

MBPO]:::methods; id9-->id14[Policy backprop

SVG

Dreamer]:::methods; classDef methods fill:#f96;

# Optimal Control and Planning

## What if we knew the transition dynamics

Often we do know the dynamics

- Games (e.g. Go)
- Easily modeled systems (e.g., navigating a car)
- Simulated environments (e.g, simulated robots, video games) Often we learn the dynamics
- System identification - fit unknown parameters of a known model
- Learning - fit a general purpose model to observed transition data

Model-based reinforcement learning Model-based reinforcement learning: learn the transition dynamics, then figure out how to choose actions