New algorithm for sequential off-policy learning improves performance over batch methods.
problem Training policies from logged interaction data in a sequential setting.
method Combines Logarithmic Smoothing with online PAC-Bayesian tools.
result Improves performance and accelerates convergence in sequential off-policy learning.
Study optimizes portfolio allocation policies using off-policy data and constraints.
problem Optimizing portfolio allocation policies under constraints using off-policy data.
method Solves a minimax objective with off-policy estimators and online learning to control constraint violations.
result Constructs near-optimal allocation policies for various regimes of operation and constraints.
This paper simplifies OPE in large state spaces using state abstractions.
problem Accurately evaluating policies offline in large state spaces.
method Developed a backward-model-irrelevance condition and an iterative state abstraction procedure.
result Deeply-abstracted states substantially simplify OPE sample complexity.
Paper proposes a framework for reliable off-policy evaluation in reinforcement learning.
problem Quantifying uncertainty in off-policy estimates for safe deployment of target policies.
method Distributionally robust optimization for creating confidence bounds.
result Non-asymptotic and asymptotic guarantees for robust cumulative reward estimates.
Efficient RL method uses SSL for small labeled data in health outcomes.
problem Lack of precise health outcome data for reinforcement learning.
method Semi-supervised learning approach for Q-learning and value estimation.
result Method efficiently estimates Q-function and value function, robust to mis-specification.
This paper proposes a method to evaluate policies using quantile metrics, improving upon existing mean-based approaches.
problem Evaluating policies using mean-based metrics ignores the variability of outcomes, especially in skewed reward distributions.
method The paper introduces a doubly-robust inference procedure for quantile off-policy evaluation using deep conditional generative learning.
result The proposed estimator outperforms classical OPE estimators for mean outcomes in heavy-tailed reward distributions.
Study online learning with off-policy feedback in adversarial bandit problems.
problem Learning with limited direct feedback in sequential decision making.
method Proposed algorithms that adapt pessimistic reward estimators to handle unknown behavior policy.
result Guaranteed regret bounds scaling with policy mismatch, improving performance against well-covered comparators.
New methods improve robust decision-making under uncertainty in off-policy evaluation.
problem Statistical uncertainty and causal considerations in off-policy evaluation.
method Marginal Ratio (MR) estimator, Conformal Off-Policy Prediction (COPP), causal bounds.
result Improved robustness and uncertainty quantification in off-policy decision-making.
New method for off-policy evaluation in POMDPs using future-dependent value functions.
problem Curse of horizon in off-policy evaluation for POMDPs.
method Develops future-dependent value functions and minimax learning method.
result PAC result and Bellman completeness for the proposed OPE estimator.
New reinforcement learning bound improves generalization for sequential data.
problem Challenges in obtaining generalization guarantees for reinforcement learning due to sequential data.
method PAC-Bayesian reinforcement learning with consideration of Markov dependencies and mixing time.
result Demonstrated practical utility through PB-SAC, providing meaningful confidence certificates.
Study off-policy evaluation and learning in dynamic pricing with context.
problem Dynamic personalized pricing and operations management problems with high-dimensional user types.
method Formalize causal structure, leverage single time-step evaluation, estimate marginal MDP.
result Improved out-of-sample policy performance in dynamic and capacitated pricing.
New method uses online learning to improve AIPW estimators for adaptively collected data.
problem Estimating treatment effects with adaptively collected data.
method Online learning to minimize sequentially weighted estimation error.
result Local minimax lower bound shows optimality of AIPW estimator.
New methods for anytime-valid off-policy inference in contextual bandits.
problem Estimating properties of hypothetical policies in adaptive experiments.
method Modern martingale techniques for comprehensive OPE inference.
result Valid anytime inference for off-policy mean reward values and entire reward distributions.
The paper explains why estimating a history-dependent policy can reduce MSE in reinforcement learning.
problem Understanding why history-dependent policies can improve MSE in off-policy evaluation.
method The paper derives a bias-variance decomposition of MSE for various OPE estimators, showing how history-dependent policies can decrease variance and increase bias.
result History-dependent policies can decrease the variance of importance sampling estimators, leading to lower MSE.
New approach to off-policy evaluation connects causal graph to policy effects.
problem Evaluating policies using observational data from different policies.
method Formalizes off-policy evaluation within a causal graph framework.
result Identifies specific causal estimands and highlights necessary experimental data.
Improved off-policy evaluation for MDPs with weak distributional overlap.
problem Evaluation of policies when target and data-collection distributions are not strongly overlapping.
method Truncated Doubly Robust (TDR) estimators for off-policy evaluation in MDPs under weak distributional overlap.
result TDR estimators can recover large-sample behavior and are consistent even when distribution ratios are not square-integrable.
Off-policy learning exhibits greater instability when compared to on-policy learning in reinforcement learning (RL). The difference in probability distribution between the target policy (π) and the behavior policy (b) is a major cause of instability. High variance also originates from distributional mismatch. The var…
We study the problem of off-policy value evaluation in reinforcement learning (RL), where one aims to estimate the value of a new policy based on data collected by a different policy. This problem is often a critical step when applying RL in real-world problems. Despite its importance, existing general methods either h…
New method estimates policy performance under unobserved confounding.
problem Estimating policy performance when decisions depend on unobserved variables.
method Developed worst-case bounds for robust OPE under unobserved confounding.
result Efficient procedure for computing worst-case bounds, proving statistical consistency.
Evolutionary Strategies optimize hyper-parameters for off-policy learning.
problem Hyper-parameter sensitivity in off-policy learning.
method Application of Evolutionary Strategies for online hyper-parameter tuning.
result Our method outperforms state-of-the-art baselines.
Model-free deep reinforcement learning (RL) algorithms have been successfully applied to a range of challenging sequential decision making and control tasks. However, these methods typically suffer from two major challenges: high sample complexity and brittleness to hyperparameters. Both of these challenges limit the a…
Adapts GRPO for off-policy RL, improving reward.
problem Improving training stability and efficiency in RL.
method Adapts GRPO to off-policy setting, uses clipped surrogate objectives.
result Off-policy GRPO outperforms on-policy GRPO in empirical tests.
Proposes a method to improve treatment policies in data-scarce clinical settings.
problem Improving treatment policies in data-scarce clinical settings with unobserved confounding.
method Uses a causal mechanism to model the underlying generative process and augments counterfactual trajectories with source domain priors.
result Significantly improves treatment policy performance in a simulated sepsis treatment task.
This paper extends off-policy reinforcement learning to the multi-agent case in which a set of networked agents communicating with their neighbors according to a time-varying graph collaboratively evaluates and improves a target policy while following a distinct behavior policy. To this end, the paper develops a multi-…
Bayesian optimization for long-term outcomes using fast and slow experiments.
problem Optimizing long-term system effects with short-term misleading results.
method Combining fast and slow experiments for Bayesian optimization.
result Sequential optimization over large action spaces in a short time.
The paper introduces a novel method for stable off-policy learning using value function chaining.
problem Stability issues in off-policy reinforcement learning.
method The approach involves learning on-policy first, then chaining off-policy value estimates.
result The method guarantees convergence and can approximate off-policy TD solutions.
Paper proposes a new method for sampling from complex distributions.
problem Sampling from unnormalised density functions in complex distributions.
method Combines amortised and particle-based methods with reinforcement learning.
result Improves sampling from complex distributions compared to existing methods.
Temporal difference learning and Residual Gradient methods are the most widely used temporal difference based learning algorithms; however, it has been shown that none of their objective functions is optimal w.r.t approximating the true value function V. Two novel algorithms are proposed to approximate the true value…
Study evaluates policies in partially observable environments without full model specification.
problem Evaluating policies in partially observable environments without full model specification.
method Developed non-parametric identification and recursive fitted-Q-evaluation algorithm.
result Established finite-sample error bounds for policy value estimation.
Memory-efficient algorithm reduces variance in off-policy RL.
problem High variance in off-policy policy optimization.
method Memory-efficient, stochastically variance-reduced algorithm using off-policy samples.
result Empirically validated effectiveness of the proposed algorithm.
Paper improves bootstrapping for off-policy reinforcement learning inference.
problem Improving bootstrapping for off-policy reinforcement learning inference.
method Proposes a bootstrapping FQE method for off-policy statistical inference and a subsampling procedure to improve runtime.
result Asymptotically efficient and distributionally consistent bootstrapping FQE method for off-policy inference.
RO-TD learns sparse value functions efficiently.
problem Learning sparse value functions efficiently.
method RO-TD integrates off-policy convergent gradient TD methods and online convex regularization.
result RO-TD learns sparse value functions with low computational complexity.
This work studies the problem of batch off-policy evaluation for Reinforcement Learning in partially observable environments. Off-policy evaluation under partial observability is inherently prone to bias, with risk of arbitrarily large errors. We define the problem of off-policy evaluation for Partially Observable Mark…
It has long been assumed that high dimensional continuous control problems cannot be solved effectively by discretizing individual dimensions of the action space due to the exponentially large number of bins over which policies would have to be learned. In this paper, we draw inspiration from the recent success of sequ…
Off-policy deep reinforcement learning (RL) algorithms are incapable of learning solely from batch offline data without online interactions with the environment, due to the phenomenon known as \textit{extrapolation error}. This is often due to past data available in the replay buffer that may be quite different from th…
We study the problem of off-policy critic evaluation in several variants of value-based off-policy actor-critic algorithms. Off-policy actor-critic algorithms require an off-policy critic evaluation step, to estimate the value of the new policy after every policy gradient update. Despite enormous success of off-policy …
Novel LSE estimator improves off-policy learning and evaluation.
problem High variance and poor performance with low-quality propensity scores and heavy-tailed reward distributions.
method Introduces a novel estimator based on the log-sum-exponential (LSE) operator.
result Achieves convergence rate of O(n−ε/(1+ε)) for regret bounds. Boosting for off-policy learning reduces empirical risk.
problem Learning from logged bandit feedback without labeled data.
method A boosting algorithm optimizing policy's expected reward.
result Excess empirical risk decreases with each round of boosting.
Off-policy reinforcement learning aims to leverage experience collected from prior policies for sample-efficient learning. However, in practice, commonly used off-policy approximate dynamic programming methods based on Q-learning and actor-critic methods are highly sensitive to the data distribution, and can make only …
The principal contribution of this paper is a conceptual framework for off-policy reinforcement learning, based on conditional expectations of importance sampling ratios. This framework yields new perspectives and understanding of existing off-policy algorithms, and reveals a broad space of unexplored algorithms. We th…
SUNRISE improves off-policy RL algorithms by integrating ensemble methods.
problem Stability and exploration issues in off-policy RL algorithms.
method SUNRISE combines ensemble-based weighted Bellman backups and upper-confidence bounds for efficient exploration.
result SUNRISE improves the performance of off-policy RL algorithms across various domains.
Stabilizes policy optimization with off-policy data using divergence augmentation.
problem Premature convergence and instability in policy optimization with off-policy data.
method Incorporates Bregman divergence between behavior and current policies to ensure safe policy updates.
result Empirically shows better performance in data-scarce scenarios compared to other algorithms.
HO2 learns options from data efficiently, improving robot manipulation tasks.
problem Learning options from raw pixel inputs in 3D robot manipulation tasks.
method HO2 infers likely option choices and trains all policy components off-policy.
result HO2 outperforms existing methods on 3D robot manipulation tasks.
This paper reviews off-policy evaluation methods in reinforcement learning.
problem Efficiency and accuracy of off-policy evaluation methods in reinforcement learning.
method Discussion of existing OPE methods, their statistical properties, and related research directions.
result Efficiency bounds and state-of-the-art OPE methods in reinforcement learning.
New algorithms improve policy evaluation in reinforcement learning.
problem Off-policy stability and on-policy efficiency issues in policy evaluation.
method Introduced novel algorithms using oblique projection method.
result Demonstrated both off-policy stability and on-policy efficiency.
Monotonic policy improvement and off-policy learning are two main desirable properties for reinforcement learning algorithms. In this paper, by lower bounding the performance difference of two policies, we show that the monotonic policy improvement is guaranteed from on- and off-policy mixture samples. An optimization …
We propose and analyze an alternate approach to off-policy multi-step temporal difference learning, in which off-policy returns are corrected with the current Q-function in terms of rewards, rather than with the target policy in terms of transition probabilities. We prove that such approximate corrections are sufficien…
This paper investigates the problem of online prediction learning, where learning proceeds continuously as the agent interacts with an environment. The predictions made by the agent are contingent on a particular way of behaving, represented as a value function. However, the behavior used to select actions and generate…