PI-ARS: Accelerating Evolution-Learned Visual-Locomotion with Predictive Information Representations. (arXiv:2207.13224v1 [cs.RO])

Evolution Strategy (ES) algorithms have shown promising results in training
complex robotic control policies due to their massive parallelism capability,
simple implementation, effective parameter-space exploration, and fast training
time. However, a key limitation of ES is its scalability to large capacity
models, including modern neural network architectures. In this work, we develop
Predictive Information Augmented Random Search (PI-ARS) to mitigate this
limitation by leveraging recent advancements in representation learning to
reduce the parameter search space for ES. Namely, PI-ARS combines …

arxiv evolution information pi predictive