Linear temporal logic (LTL) offers a simplified way of specifying tasks ...
We present Revel, a partially neural reinforcement learning (RL) framewo...
We study the problem of learning differentiable functions expressed as
p...
We present Imitation-Projected Policy Gradient (IPPG), an algorithmic
fr...
We study the problem of programmatic reinforcement learning, in which
po...
Dealing with high variance is a significant challenge in model-free
rein...
We investigate the internal representations that a recurrent neural netw...
We study the problem of generating interpretable and verifiable policies...