How to design efficient algorithms is a central problem for reinforcement learning (RL).

The standard assumption in reinforcement learning (RL) is that agents observe feedback for their actions immediately. However, in practice feedback is often observedindelay.

This paper studies a recent proposal to use randomized value functions to drive exploration in reinforcement learning.

Empowered by neural networks, deep reinforcement learning (DRL) achieves tremendous empirical success. However, DRL requires a large dataset by interacting with the environment, which is unrealistic in critical scenarios such as autonomous driving and personalized medicine. In this paper, we study how to incorporate the dataset collected in the offline setting to improve the sample efficiency in the online setting. To incorporate the observational data, we face two challenges.

During the exploration phase, an agent collects samples without using a pre-specified reward function. After the exploration phase, a reward function is given, and the agent uses samples collected during the exploration phase to computeanear-optimalpolicy.

We address the issue of safety in reinforcement learning. We pose the problem in an episodic framework of a constrained Markov decision process.

Designing efficient reinforcement learning (RL) algorithms for environments with large state and action spaces is one of the main tasks in the RL community.

Real-world reinforcement learning (RL) applications often come with possibly infinite state and action space, and in such a situation classical RL algorithms developed in the tabular setting are not applicable anymore. A popular approach to overcoming this issue is by applying function approximation techniques to the underlying structures of the Markovdecision processes (MDPs).

Priorworksonadversarial attacks againstRLmainly focus on either observation poisoning attacks or environment poisoning attacks.