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

What policy should be employed in a Markov decision process with uncertain parameters?

Deep model-free reinforcement learning has achieved great successes in recent years, notably in video games [11], board games [19], robotics [10], and challenging control tasks [17,5].

Actor-critic methods, a type of model-free Reinforcement Learning, have beensuccessfully applied to challenging tasks in continuous control, often achievingstate-of-the artperformance.

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

Theempirical results demonstrate that this framework can improve the answers for multi-agent decision-making problems by showing superior performance on the training and unseen tasks of the StarCraft Multi-Agent Challenge benchmark.

The idea is to evolve a differentiable loss function, such thatanagent, which optimizes itspolicytominimize thisloss, willachieve highrewards.

There are plenty of previous studies targeting the problem from different aspects. For temporal point process, agreat number of works [3, 13, 15, 16, 28] attempt to model the intensify function from statistic views, and recent studies harness deep recurrent model [24], generative adversarial network [23] and reinforcement learning [19, 18] to learn the temporal process. These researches mainly focus on one-dimension eventsequences where eacheventpossesses thesame marker.

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