Latent Imagination Facilitates Zero-Shot Transfer in Autonomous Racing
Axel Brunnbauer,Luigi Berducci,Andreas Brandstátter,Mathias Lechner,Ramin Hasani,Daniela Rus,Radu Grosu,Axel Brunnbauer,Luigi Berducci,Andreas Brandstátter,Mathias Lechner,Ramin Hasani,Daniela Rus,Radu Grosu
World models learn behaviors in a latent imagination space to enhance the sample-efficiency of deep reinforcement learning (RL) algorithms. While learning world models for high-dimensional observations (e.g., pixel inputs) has become practicable on standard RL benchmarks and some games, their effectiveness in real-world robotics applications has not been explored. In this paper, we investigate how...
