Unsupervised Reinforcement Learning
22 papers with code • 8 benchmarks • 2 datasets
On a variety of simulated robotic tasks, we show that this simple objective results in the unsupervised emergence of diverse skills, such as walking and jumping.
Can we instead develop efficient reinforcement learning methods that acquire diverse skills without any reward function, and then repurpose these skills for downstream tasks?
Along this line, we address the problem of unsupervised reinforcement learning in a class of multiple environments, in which the policy is pre-trained with interactions from the whole class, and then fine-tuned for several tasks in any environment of the class.
Every living organism struggles against disruptive environmental forces to carve out and maintain an orderly niche.