Reinforcement learning (RL) is typically concerned with estimating stationary policies orsingle-step models, leveraging theMarkovproperty tofactorize problems in time. However, we can also view RL as a generic sequence modeling problem, with the goal being to produce a sequence of actions that leads to a sequence ofhighrewards.

Many real-world domains require safe decision making in uncertain environments. In this work, we introduce a deep reinforcement learning framework for approaching this important problem. We consider a distribution over transition models, and apply a risk-averse perspective towards model uncertainty through the use of coherent distortion risk measures.

The pressure for survival prohibits slow, linear adaptation to different goals, i.e., learning value functions from scratch for each new objective. A quick and versatile paradigm is necessary forsuchgoal-directed learning scenarios.