Evolution strategies as a scalable alternative to reinforcement learning
Evolution strategies rival standard RL on Atari/MuJoCo benchmarks while eliminating replay buffers and hyperparameter sensitivity, offering a scalable alternative for training.
Excerpt
We’ve discovered that evolution strategies (ES), an optimization technique that’s been known for decades, rivals the performance of standard reinforcement learning (RL) techniques on modern RL benchmarks (e.g. Atari/MuJoCo), while overcoming many of RL’s inconveniences.
Read at source: https://openai.com/index/evolution-strategies