Related papers: Leveraging Factored Action Spaces for Off-Policy E…
We study the problem of offline policy optimization in stochastic contextual bandit problems, where the goal is to learn a near-optimal policy based on a dataset of decision data collected by a suboptimal behavior policy. Rather than making…
We consider off-policy evaluation (OPE) of deterministic target policies for reinforcement learning (RL) in environments with continuous action spaces. While it is common to use importance sampling for OPE, it suffers from high variance…
This paper investigates the off-policy evaluation (OPE) problem from a distributional perspective. Rather than focusing solely on the expectation of the total return, as in most existing OPE methods, we aim to estimate the entire return…
Off-policy evaluation (OPE) estimates the value of a contextual bandit policy prior to deployment. As such, OPE plays a critical role in ensuring safety in high-stakes domains such as healthcare. However, standard OPE approaches are limited…
Expanding reinforcement learning (RL) to offline domains generates promising prospects, particularly in sectors where data collection poses substantial challenges or risks. Pivotal to the success of transferring RL offline is mitigating…
We study Off-Policy Evaluation (OPE) in contextual bandit settings with large action spaces. The benchmark estimators suffer from severe bias and variance tradeoffs. Parametric approaches suffer from bias due to difficulty specifying the…
Offline reinforcement learning algorithms often require careful hyperparameter tuning. Before deployment, we need to select amongst a set of candidate policies. However, there is limited understanding about the fundamental limits of this…
We consider the off-policy estimation problem of estimating the expected reward of a target policy using samples collected by a different behavior policy. Importance sampling (IS) has been a key technique to derive (nearly) unbiased…
Off-Policy Evaluation (OPE) is employed to assess the potential impact of a hypothetical policy using logged contextual bandit feedback, which is crucial in areas such as personalized medicine and recommender systems, where online…
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…
Policy gradient methods can solve complex tasks but often fail when the dimensionality of the action-space or objective multiplicity grow very large. This occurs, in part, because the variance on score-based gradient estimators scales…
Policy-based methods have achieved remarkable success in solving challenging reinforcement learning problems. Among these methods, off-policy policy gradient methods are particularly important due to that they can benefit from off-policy…
We consider the problem of off-policy evaluation for reinforcement learning, where the goal is to estimate the expected reward of a target policy $\pi$ using offline data collected by running a logging policy $\mu$. Standard…
We consider off-policy evaluation (OPE) in contextual bandits with finite action space. Inverse Propensity Score (IPS) weighting is a widely used method for OPE due to its unbiased, but it suffers from significant variance when the action…
Many large MDPs can be represented compactly using a dynamic Bayesian network. Although the structure of the value function does not retain the structure of the process, recent work has shown that value functions in factored MDPs can often…
In this work, we propose marginalized operators, a new class of off-policy evaluation operators for reinforcement learning. Marginalized operators strictly generalize generic multi-step operators, such as Retrace, as special cases.…
A central challenge to applying many off-policy reinforcement learning algorithms to real world problems is the variance introduced by importance sampling. In off-policy learning, the agent learns about a different policy than the one being…
Policy optimization is an effective reinforcement learning approach to solve continuous control tasks. Recent achievements have shown that alternating online and offline optimization is a successful choice for efficient trajectory reuse.…
Off-policy evaluation and learning in contextual bandits use logged interaction data to estimate and optimize the value of a target policy. Most existing methods require sufficient action overlap between the logging and target policies, and…
This paper studies the evaluation of policies that recommend an ordered set of items (e.g., a ranking) based on some context---a common scenario in web search, ads, and recommendation. We build on techniques from combinatorial bandits to…