We study risk-sensitive reinforcement learning (RL) based on the entropic risk measure. Although existing works have established non-asymptotic regret guarantees for this problem, they leave open an exponential gap between the upper and lower bounds. We identify the deficiencies in existing algorithms and their analysis that result in such a gap.

NVI learns proposals by optimizing a divergence at each level of nesting.

In many sequential decision making settings, the agent lacks complete information about the underlying state of the system, a phenomenon known as partial observability .

We appreciate your positive feedback and will revise our presentation accordingly. Prior to this work, the walk length of DeepWalk has to be selected by cross-validation. Thank you for your comments. We appreciate your views and we would like to clarify a few points. We are open to reframing the work as "Matrix Thank you for your comments.

The vast majority of work in self-supervised learning have focused on assessing recovered features by a chosen set of downstream tasks.

The vast majority of work in self-supervised learning have focused on assessing recovered features by a chosen set of downstream tasks.

We study reinforcement learning in non-episodic factored Markov decision processes (FMDPs).