Related papers: Infinite-horizon Off-Policy Policy Evaluation with…
Off-Policy Evaluation (OPE) is an important practical problem in algorithmic ranking systems, where the goal is to estimate the expected performance of a new ranking policy using only offline logged data collected under a different, logging…
While the classic off-policy evaluation (OPE) literature commonly assumes decision time points to be evenly spaced for simplicity, in many real-world scenarios, such as those involving user-initiated visits, decisions are made at…
We revisit the finite time analysis of policy gradient methods in the one of the simplest settings: finite state and action MDPs with a policy class consisting of all stochastic policies and with exact gradient evaluations. There has been…
Off-policy Evaluation (OPE) methods are crucial tools for evaluating policies in high-stakes domains such as healthcare, where direct deployment is often infeasible, unethical, or expensive. When deployment environments are expected to…
This paper deals with optimal policy learning (OPL) with observational data, i.e. data-driven optimal decision-making, in multi-action (or multi-arm) settings, where a finite set of decision options is available. It is organized in three…
Many sequential decision making problems are high-stakes and require off-policy evaluation (OPE) of a new policy using historical data collected using some other policy. One of the most common OPE techniques that provides unbiased estimates…
Off-policy evaluation (OPE) methods aim to estimate the value of a new reinforcement learning (RL) policy prior to deployment. Recent advances have shown that leveraging auxiliary datasets, such as those synthesized by generative models,…
We study off-policy evaluation (OPE) in partially observable environments with complex observations, with the goal of developing estimators whose guarantee avoids exponential dependence on the horizon. While such estimators exist for MDPs…
This paper proposes a novel varying horizon economic model predictive control (EMPC) scheme without terminal constraints for constrained nonlinear systems with additive disturbances and unknown economic costs. The general regression…
Policy networks are a central feature of deep reinforcement learning (RL) algorithms for continuous control, enabling the estimation and sampling of high-value actions. From the variational inference perspective on RL, policy networks, when…
We apply diffusion strategies to develop a fully-distributed cooperative reinforcement learning algorithm in which agents in a network communicate only with their immediate neighbors to improve predictions about their environment. The…
Offline reinforcement learning methods typically enforce strict constraints to ensure safety; yet this rigidity often prevents the discovery of optimal behaviors outside the immediate support of the behavior policy. To address this, we…
Multi-Agent Proximal Policy Optimization (MAPPO) is a variant of the Proximal Policy Optimization (PPO) algorithm, specifically tailored for multi-agent reinforcement learning (MARL). MAPPO optimizes cooperative multi-agent settings by…
Off-policy evaluation (OPE) estimates the value of a target treatment policy (e.g., a recommender system) using data collected by a different logging policy. It enables high-stakes experimentation without live deployment, yet in practice…
On-policy reinforcement learning (RL) algorithms are widely used for their strong asymptotic performance and training stability, but they struggle to scale with larger batch sizes, as additional parallel environments yield redundant data…
Offline reinforcement learning (RL) presents distinct challenges as it relies solely on observational data. A central concern in this context is ensuring the safety of the learned policy by quantifying uncertainties associated with various…
In this work, we consider the problem of model selection for deep reinforcement learning (RL) in real-world environments. Typically, the performance of deep RL algorithms is evaluated via on-policy interactions with the target environment.…
We study the problem of off-policy evaluation (OPE) for episodic Partially Observable Markov Decision Processes (POMDPs) with continuous states. Motivated by the recently proposed proximal causal inference framework, we develop a…
Markov control algorithms that perform smooth, non-greedy updates of the policy have been shown to be very general and versatile, with policy gradient and Expectation Maximisation algorithms being particularly popular. For these algorithms,…
Coupon allocation drives customer purchases and boosts revenue. However, it presents a fundamental trade-off between exploiting the current optimal policy to maximize immediate revenue and exploring alternative policies to collect data for…