The burgeoning development of the cloud market has promoted the expansion of resources
held by cloud providers, but the resulting underutilization caused by the over-provisioned …

Realistic environments often provide agents with very limited feedback. When the
environment is initially unknown, the feedback, in the beginning, can be completely absent …

While much progress has been made in understanding the minimax sample complexity of
reinforcement learning (RL)---the complexity of learning on the worst-case''instance---such …

Reward-free exploration is a reinforcement learning setting recently studied by (Jin et al.
2020), who address it by running several algorithms with regret guarantees in parallel. In our …

In some applications of reinforcement learning, a dataset of pre-collected experience is
already availablebut it is also possible to acquire some additional online data to help …

This paper presents new deviation inequalities that are valid uniformly in time under
adaptive sampling in a multi-armed bandit model. The deviations are measured using the …

Inverse reinforcement learning (IRL) denotes a powerful family of algorithms for recovering a
reward function justifying the behavior demonstrated by an expert agent. A well-known …

The theory of reinforcement learning has focused on two fundamental problems: achieving
low regret, and identifying $\epsilon $-optimal policies. While a simple reduction allows one …

We address the challenge of exploration in reinforcement learning (RL) when the agent
operates in an unknown environment with sparse or no rewards. In this work, we study the …

We consider reinforcement learning in an environment modeled by an episodic, tabular,
step-dependent Markov decision process of horizon $ H $ with $ S $ states, and $ A …