The promise of reinforcement learning is to solve complex sequential decision problems autonomously by specifying a high-level reward function only. However, algorithms struggle when, as often the case, simple and intuitive rewards provide sparse deceptive feedback. Avoiding these pitfalls requires thoroughly exploring environment, but creating that can do so remains one central challenges fiel...

0

Many real-world analytics problems involve two significant challenges: prediction and optimization. Because of the typically complex nature each challenge, standard paradigm is predict-then-optimize. By large, machine learning tools are intended to minimize error do not account for how predictions will be used in downstream optimization problem. In contrast, we propose a new very general framew...