Reinforcement learning is an essential paradigm for solving sequential decision problems
under uncertainty. Despite many remarkable achievements in recent decades, applying …

In reinforcement learning (RL), balancing exploration and exploitation is crucial for
achieving an optimal policy in a sample-efficient way. To this end, existing sample-efficient …

We study off-policy evaluation (OPE) for partially observable MDPs (POMDPs) with general
function approximation. Existing methods such as sequential importance sampling …

With the fast improvement of machine learning, reinforcement learning (RL) has been used
to automate human tasks in different areas. However, training such agents is difficult and …

The general sequential decision-making problem, which includes Markov decision
processes (MDPs) and partially observable MDPs (POMDPs) as special cases, aims at …

Abstract Offline Reinforcement Learning (RL) has demonstrated promising results in various
applications by learning policies from previously collected datasets, reducing the need for …

This paper deals with offline (or batch) Reinforcement Learning (RL) in episodic Regular
Decision Processes (RDPs). RDPs are the subclass of Non-Markov Decision Processes …

In this paper, we propose a policy gradient method for confounded partially observable
Markov decision processes (POMDPs) with continuous state and observation spaces in the …

Offline reinforcement learning (RL) can in principle synthesize more optimal behavior from a
dataset consisting only of suboptimal trials. One way that this can happen is by" stitching" …

This work studies offline Reinforcement Learning (RL) in a class of non-Markovian
environments called Regular Decision Processes (RDPs). In RDPs, the unknown …