Better Safe than Sorry: Evidence Accumulation Allows for Safe Reinforcement Learning

24 Sep 2018Akshat AgarwalAbhinau Kumar VKyle DunovanErik PetersonTimothy VerstynenKatia Sycara

In the real world, agents often have to operate in situations with incomplete information, limited sensing capabilities, and inherently stochastic environments, making individual observations incomplete and unreliable. Moreover, in many situations it is preferable to delay a decision rather than run the risk of making a bad decision... (read more)

PDF Abstract

Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.