There are still, however, some unsolved challenges for a successful deployment of RL such as efficient learning of constrained or safe Markov Decision Processes (MDPs) [4].

This creates a tight feedback loop between representation learning,memory,reinforcementlearning,andsampling-basedplanning.

Understanding emerging behaviors of reinforcement learning (RL) agents may be difficult since such agents are often trained in complex environments using highly complex decision making procedures.

The history of learning for control has been an exciting back and forth between twobroad classes ofalgorithms: planning andreinforcement learning.

Neural Information Processing Systems http://nips.cc/

It also does not enjoy SNIS's inherent stability and boundedness.