Neural Architecture Evolution in Deep Reinforcement Learning for Continuous Control [article]

Jörg K.H. Franke, Gregor Köhler, Noor Awad, Frank Hutter
2020 arXiv   pre-print
Current Deep Reinforcement Learning algorithms still heavily rely on handcrafted neural network architectures. We propose a novel approach to automatically find strong topologies for continuous control tasks while only adding a minor overhead in terms of interactions in the environment. To achieve this, we combine Neuroevolution techniques with off-policy training and propose a novel architecture mutation operator. Experiments on five continuous control benchmarks show that the proposed
more » ... itic Neuroevolution algorithm often outperforms the strong Actor-Critic baseline and is capable of automatically finding topologies in a sample-efficient manner which would otherwise have to be found by expensive architecture search.
arXiv:1910.12824v3 fatcat:c6z54jty2ff2bmbxjwctefraru