See Table 1for the average running time per problem instance. Note that the implementation of Z3 and OR-tools22 are in C++, while NeuRewriter and RL baselines are in Python. Still, we can observethat our approach achieves a23 better balance between the time-efficiency and the result quality. For expression simplification and job scheduling,24 NeuRewriter is even more time-efficient than Z3 and OR-tools. The region-pickerπω is parameterized by aQ-function and is similar in spirit to soft-Q learning [2].

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

When one agent interacts with a multi-agent environment, it is challenging to deal with various opponents unseen before.

Define = log (M2H / ).

Deep reinforcement learning has enjoyed recent success in domains like games [1, 2], robotic manipulation,andlocomotiontasks[3,4].

A key algorithmic insight is that optimism may lead to over-exploration even for two-layer neural net model class.

Our RADIAL-RL agents consistently outperform prior methods when tested against attacks of varying strength and are more computationally efficient to train. In addition, we propose a new evaluation method calledGreedyWorst-Case Reward(GWC) tomeasure attack agnostic robustness of deep RL agents. We show that GWC can be evaluated efficiently and is a good estimate of the reward under the worst possible sequence of adversarial attacks.

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