Importance sampling-based estimators for off-policy evaluation (OPE) are valued for their simplicity, unbiasedness, and reliance on relatively few assumptions. However, the variance of these estimators is often high, especially when trajectories are
of different lengths. In this work, we introduce Omitting-States-Irrelevant-to-Return Importance Sampling (OSIRIS), an estimator which reduces variance by strategically omitting likelihood ratios associated with certain states. We formalize the conditions under which OSIRIS is unbiased and has lower variance than ordinary importance sampling, and we demonstrate these properties empirically.
The fundamental assumption of reinforcement learning in Markov decision processes (MDPs) is that the relevant decision process is, in fact, Markov. However, when MDPs have rich observations, agents typically learn by way of an abstract state represen
tation, and such representations are not guaranteed to preserve the Markov property. We introduce a novel set of conditions and prove that they are sufficient for learning a Markov abstract state representation. We then describe a practical training procedure that combines inverse model estimation and temporal contrastive learning to learn an abstraction that approximately satisfies these conditions. Our novel training objective is compatible with both online and offline training: it does not require a reward signal, but agents can capitalize on reward information when available. We empirically evaluate our approach on a visual gridworld domain and a set of continuous control benchmarks. Our approach learns representations that capture the underlying structure of the domain and lead to improved sample efficiency over state-of-the-art deep reinforcement learning with visual features -- often matching or exceeding the performance achieved with hand-designed compact state information.
Finding an effective medical treatment often requires a search by trial and error. Making this search more efficient by minimizing the number of unnecessary trials could lower both costs and patient suffering. We formalize this problem as learning a
policy for finding a near-optimal treatment in a minimum number of trials using a causal inference framework. We give a model-based dynamic programming algorithm which learns from observational data while being robust to unmeasured confounding. To reduce time complexity, we suggest a greedy algorithm which bounds the near-optimality constraint. The methods are evaluated on synthetic and real-world healthcare data and compared to model-free reinforcement learning. We find that our methods compare favorably to the model-free baseline while offering a more transparent trade-off between search time and treatment efficacy.
Off-policy evaluation in reinforcement learning offers the chance of using observational data to improve future outcomes in domains such as healthcare and education, but safe deployment in high stakes settings requires ways of assessing its validity.
Traditional measures such as confidence intervals may be insufficient due to noise, limited data and confounding. In this paper we develop a method that could serve as a hybrid human-AI system, to enable human experts to analyze the validity of policy evaluation estimates. This is accomplished by highlighting observations in the data whose removal will have a large effect on the OPE estimate, and formulating a set of rules for choosing which ones to present to domain experts for validation. We develop methods to compute exactly the influence functions for fitted Q-evaluation with two different function classes: kernel-based and linear least squares, as well as importance sampling methods. Experiments on medical simulations and real-world intensive care unit data demonstrate that our method can be used to identify limitations in the evaluation process and make evaluation more robust.
Tensor decomposition methods allow us to learn the parameters of latent variable models through decomposition of low-order moments of data. A significant limitation of these algorithms is that there exists no general method to regularize them, and in
the past regularization has mostly been performed using bespoke modifications to the algorithms, tailored for the particular form of the desired regularizer. We present a general method of regularizing tensor decomposition methods which can be used for any likelihood model that is learnable using tensor decomposition methods and any differentiable regularization function by supplementing the training data with pseudo-data. The pseudo-data is optimized to balance two terms: being as close as possible to the true data and enforcing the desired regularization. On synthetic, semi-synthetic and real data, we demonstrate that our method can improve inference accuracy and regularize for a broad range of goals including transfer learning, sparsity, interpretability, and orthogonality of the learned parameters.
We consider a model-based approach to perform batch off-policy evaluation in reinforcement learning. Our method takes a mixture-of-experts approach to combine parametric and non-parametric models of the environment such that the final value estimate
has the least expected error. We do so by first estimating the local accuracy of each model and then using a planner to select which model to use at every time step as to minimize the return error estimate along entire trajectories. Across a variety of domains, our mixture-based approach outperforms the individual models alone as well as state-of-the-art importance sampling-based estimators.
In this work, we consider the problem of estimating a behaviour policy for use in Off-Policy Policy Evaluation (OPE) when the true behaviour policy is unknown. Via a series of empirical studies, we demonstrate how accurate OPE is strongly dependent o
n the calibration of estimated behaviour policy models: how precisely the behaviour policy is estimated from data. We show how powerful parametric models such as neural networks can result in highly uncalibrated behaviour policy models on a real-world medical dataset, and illustrate how a simple, non-parametric, k-nearest neighbours model produces better calibrated behaviour policy estimates and can be used to obtain superior importance sampling-based OPE estimates.
Despite the apparent ease with which a sheet of paper is crumpled and tossed away, crumpling dynamics are often considered a paradigm of complexity. This complexity arises from the infinite number of configurations a disordered crumpled sheet can tak
e. Here we experimentally show that key aspects of crumpling have a very simple description; the evolution of the damage in crumpling dynamics can largely be described by a single global quantity, the total length of all creases. We follow the evolution of the damage network in repetitively crumpled elastoplastic sheets, and show that the dynamics of this quantity are deterministic, and depend only on the instantaneous state of the crease network and not at all on the crumpling history. We also show that this global quantity captures the crumpling dynamics of a sheet crumpled for the first time. This leads to a remarkable reduction in complexity, allowing a description of a highly disordered system by a single state parameter. Similar strategies may also be useful in analyzing other systems that evolve under geometric and mechanical constraints, from faulting of tectonic plates to the evolution of proteins.
Much attention has been devoted recently to the development of machine learning algorithms with the goal of improving treatment policies in healthcare. Reinforcement learning (RL) is a sub-field within machine learning that is concerned with learning
how to make sequences of decisions so as to optimize long-term effects. Already, RL algorithms have been proposed to identify decision-making strategies for mechanical ventilation, sepsis management and treatment of schizophrenia. However, before implementing treatment policies learned by black-box algorithms in high-stakes clinical decision problems, special care must be taken in the evaluation of these policies. In this document, our goal is to expose some of the subtleties associated with evaluating RL algorithms in healthcare. We aim to provide a conceptual starting point for clinical and computational researchers to ask the right questions when designing and evaluating algorithms for new ways of treating patients. In the following, we describe how choices about how to summarize a history, variance of statistical estimators, and confounders in more ad-hoc measures can result in unreliable, even misleading estimates of the quality of a treatment policy. We also provide suggestions for mitigating these effects---for while there is much promise for mining observational health data to uncover better treatment policies, evaluation must be performed thoughtfully.
We study the problem of off-policy policy evaluation (OPPE) in RL. In contrast to prior work, we consider how to estimate both the individual policy value and average policy value accurately. We draw inspiration from recent work in causal reasoning,
and propose a new finite sample generalization error bound for value estimates from MDP models. Using this upper bound as an objective, we develop a learning algorithm of an MDP model with a balanced representation, and show that our approach can yield substantially lower MSE in common synthetic benchmarks and a HIV treatment simulation domain.
