In real life, success is often contingent upon multiple critical steps that are distant in time from each other and from the final reward.

Weintroduceanaturalquantity,the teaching risk, which measures the potential suboptimality of policies that look optimal to the learner in this setting. We show that bounds on the teaching risk guarantee that the learner is able to find a near-optimal policy using standard algorithms basedoninversereinforcement learning. Basedonthesefindings, we suggest a teaching scheme in which the expert can decrease the teaching risk by updating the learner's worldview, and thus ultimately enable her to find a near-optimalpolicy.

VIENNA performs robust on unseen environments, through learning task-shared, general representations.

Though promising results have been reported on some RL application domains, policies learned with such representations usually fail to generalize well in a complex environment because minimizing a reconstruction loss may potentially introduce local (visual) features with task-irrelevant information.

Though promising results have been reported on some RL application domains, policies learned with such representations usually fail to generalize well in a complex environment because minimizing a reconstruction loss may potentially introduce local (visual) features with task-irrelevant information.

Reinforcement Learning (RL) has achievedimpressiveprogress inrecent years, such asresults in Atari [24] and Go [28] in which RL agents even perform better than human beings.

Our framework is the infinite-horizon discounted Markov Decision Process (MDP).

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

In this work, we introduce a framework for policy optimization based on mirror descent that naturally accommodates general parameterizations. The policy class induced by our scheme recovers known classes, e.g., softmax, and generates new ones depending on the choice of mirror map.