all AI news
Overcoming Exploration: Deep Reinforcement Learning in Complex Environments from Temporal Logic Specifications. (arXiv:2201.12231v3 [cs.RO] UPDATED)
cs.LG updates on arXiv.org arxiv.org
Exploration is a fundamental challenge in Deep Reinforcement Learning (DRL)
based model-free navigation control since typical exploration techniques for
target-driven navigation tasks rely on noise or greedy policies, which are
sensitive to the density of rewards. In practice, robots are always deployed in
complex cluttered environments, containing dense obstacles and narrow
passageways, raising natural spare rewards that are hard to be explored for
training. Such a problem becomes even more serious when pre-defined tasks are
complex and have rich expressivity. …
arxiv environments exploration logic reinforcement reinforcement learning temporal