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…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
169,051 papers · 148 categories
Trend · papers per month
48 results for “off-policy correction”
New method estimates state-action stationary distribution for better off-policy policy evaluation.
problem Accurately estimating state-action stationary distribution for off-policy policy evaluation.
method Estimated Mixture Policy (EMP) for state and state-action stationary distribution corrections.
result Empirical validation shows improved accuracy over state-of-the-art methods.
New method corrects state distribution mismatch for off-policy policy optimization.
problem Mismatch between behavior and evaluation policy state distributions.
method Off-policy policy gradient with state distribution correction.
result Significantly improved policy quality in simulations.
Unified DICE estimators as regularized Lagrangians for improved off-policy evaluation.
problem Improving off-policy evaluation from behavior-agnostic data.
method Unified derivation of DICE estimators as regularized Lagrangians of a linear program.
result Dual solutions offer greater flexibility and provide superior estimates in practice.
Proposes a method for obtaining interval bounds in off-policy evaluation.
problem Provides provably correct upper and lower bounds for off-policy evaluation.
method Searches for the maximum and minimum values of the expected reward among Lipschitz Q-functions.
result Introduces a Lipschitz value iteration method to monotonically tighten interval bounds.
Improves YouTube's recommendation system by correcting biases in logged feedback.
problem Data biases in logged feedback from multiple behavior policies.
method Top-K off-policy correction applied to REINFORCE algorithm.
result Efficacy demonstrated through simulations and live experiments.
New estimator improves off-policy evaluation for large action spaces.
problem Conventional importance-weighting approaches suffer from excessive variance in off-policy evaluation for large discrete action spaces.
method Proposes OffCEM estimator based on conjunct effect model (CEM), applying importance weighting only to action clusters and using model-based reward estimation for residual effects.
result Proposed estimator is unbiased under local correctness condition, providing substantial improvements in OPE especially with many actions.
The paper improves off-policy evaluation in contextual bandits using conformal prediction.
problem Quantifying the performance of a target policy using data from a different behavior policy.
method Proposes a novel algorithm based on a PAC-valid conformal prediction framework to construct probably approximately correct prediction intervals.
result Establishes PAC-type bounds on coverage, improving theoretical guarantees.
A new resampling strategy, Importance Resampling, improves sample efficiency and reduces variance in off-policy prediction.
problem High variance updates in importance sampling for off-policy prediction.
method Importance Resampling (IR) resamples experience from a replay buffer and applies standard on-policy updates, avoiding importance sampling ratios.
result Importance Resampling (IR) shows improved sample efficiency and lower variance updates compared to other methods.
We consider the problem of off-policy evaluation in Markov decision processes. Off-policy evaluation is the task of evaluating the expected return of one policy with data generated by a different, behavior policy. Importance sampling is a technique for off-policy evaluation that re-weights off-policy returns to account…
STAR framework reduces OPE variance by distilling complex problems into discrete ARPs.
problem High variance and bias in off-policy evaluation methods.
method STAR framework that includes various OPE estimators and leverages state abstraction.
result Predictions from ARPs estimated from off-policy data are asymptotically correct.
DOLCE improves off-policy evaluation and learning by decomposing effects.
problem Bias in off-policy evaluation and learning due to policy mismatch.
method Uses lagged contexts and a moment-based training procedure to decompose and cancel bias.
result DOLCE achieves substantial improvements in off-policy evaluation and learning.
New method for rigorous confidence intervals in off-policy evaluation.
problem Evaluate new policies from off-policy data without executing them.
method Variational framework using kernel Bellman loss.
result Efficient method for tight confidence intervals in various settings.
Improved off-policy reinforcement learning by discounting and soft normalization.
problem Divergence issues in off-policy reinforcement learning.
method Introducing a discount factor and a soft normalization penalty into COP-TD.
result Discounted COP-TD is better behaved both theoretically and empirically.
COPP provides reliable intervals for outcomes under a new policy in contextual bandits.
problem Lack of reliable predictive intervals for outcomes under a new policy in contextual bandits.
method Conformal prediction applied to contextual bandits.
result COPP provides finite-sample guarantees without additional assumptions.
New methods improve off-policy evaluation for survival outcomes with censoring.
problem Systematic underestimation of policy performance due to censoring bias in survival outcomes.
method Proposes IPCW-IPS and IPCW-DR to handle censoring bias in survival outcomes.
result The proposed methods are unbiased and achieve double robustness.
In this paper, we explore deep reinforcement learning algorithms for vision-based robotic grasping. Model-free deep reinforcement learning (RL) has been successfully applied to a range of challenging environments, but the proliferation of algorithms makes it difficult to discern which particular approach would be best …
Unified framework for analyzing pessimism in off-policy learning with regularized importance sampling.
problem High variance in importance weighting for off-policy learning.
method Unified PAC-Bayesian study of pessimism with regularized importance sampling.
result Derivation of a tractable PAC-Bayesian generalization bound for common importance weight regularizations.
Proposes MDR estimator for unbiased OPE with large action spaces.
problem Severe bias and variance tradeoffs in OPE with large action spaces.
method Marginalized Doubly Robust (MDR) estimator, reducing variance and bias.
result MDR estimator is unbiased under weaker assumptions than MIPS.
New metric for off-policy evaluation without models or importance sampling.
problem Evaluating deep RL models in real-world environments is costly and impractical.
method Framed as a PU classification problem, using Q-function as decision function.
result Metric reliably predicts policy performance in various scenarios.
DualDICE estimates discounted distribution ratios for reinforcement learning datasets.
problem Accurate estimation of discounted stationary distribution ratios for reinforcement learning applications.
method Behavior-agnostic algorithm that avoids importance weights and is theoretically guaranteed.
result Significantly improves off-policy policy evaluation accuracy compared to existing techniques.
Corrects bias in learned generative models using likelihood-free importance weighting.
problem Bias in learned generative models relative to true data distribution.
method Estimate likelihood ratio using a classifier, apply importance weighting.
result Consistently improves goodness-of-fit metrics for deep generative models.
Improved TD learning for non-i.i.d. Markovian data.
problem Convergence analysis of two time-scale TD learning under Markovian samples.
method Non-asymptotic convergence analysis of two time-scale TD with gradient correction under Markovian data.
result Two time-scale TD can converge as fast as O(log t/(t^(2/3))) under diminishing stepsize.
POTEC tackles off-policy learning in large action spaces, improving effectiveness.
problem Existing OPL methods fail in large discrete action spaces due to bias or variance issues.
method Two-stage algorithm: cluster selection via policy-based approach, action selection via regression-based approach.
result POTEC provides substantial improvements in off-policy learning effectiveness, especially in large and structured action spaces.
Resampling outperforms reweighting for correcting biased data in machine learning models.
problem Correcting sampling bias in machine learning models trained on biased data sets.
method Compared resampling and reweighting techniques, focusing on their performance with stochastic gradient algorithms.
result Resampling outperforms reweighting when combined with stochastic gradient algorithms.
New DR-IC estimator reduces bias and variance in OPE.
problem Estimating value of a target policy using logged data from a different policy.
method DR-IC estimator that combines parametric reward model and context-based switching rule.
result DR-IC estimator outperforms state-of-the-art OPE algorithms.
Study off-policy evaluation in partially observable environments, reducing bias and errors.
problem Bias and large errors in off-policy evaluation for partially observable environments.
method Defined and solved off-policy evaluation for POMDPs, introduced Decoupled POMDP model.
result Demonstrated and compared off-policy evaluation methods, showing benefits of new approach.
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.
This study evaluates multi-step reinforcement learning methods in the Mountain Car environment.
problem Lack of statistical significance in evaluating multi-step reinforcement learning methods.
method Combines n-step action-value algorithms with DQN architecture, tests in Mountain Car environment.
result Performance varies with off-policy correction, backup length, and target network update frequency.
New method improves off-policy critic evaluation in reinforcement learning.
problem High variance and instability in off-policy policy evaluation.
method Doubly robust estimators applied to actor-critic algorithms.
result Doubly robust estimation significantly improves performance in continuous control tasks.
The paper introduces a new framework for off-policy reinforcement learning.
problem Improving off-policy reinforcement learning algorithms.
method Conceptual framework based on conditional importance sampling.
result Theoretical analysis and concrete algorithm investigation.
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.
New method reduces state distribution mismatch in off-policy RL.
problem State distribution mismatch in off-policy RL algorithms.
method Develops a novel constrained off-policy gradient objective to minimize state distribution shift.
result Minimizing state distribution shift improves performance in off-policy RL algorithms.
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.
A new estimator improves off-policy evaluation in RL, outperforming existing methods.
problem Estimating performance of a new policy using historical data from a different policy.
method Doubly-robust estimator based on Targeted Maximum Likelihood Estimation, with variance reduction techniques.
result Our estimator uniformly outperforms existing methods across various RL environments and levels of model misspecification.
New algorithm BEAR reduces instability in off-policy Q-learning.
problem High sensitivity of off-policy Q-learning methods to data distribution.
method Identified and mitigated bootstrapping error through constrained action selection.
result BEAR algorithm learns robustly from various off-policy distributions.
Paper develops a new multi-agent reinforcement learning algorithm.
problem Improving policies in a network of communicating agents.
method Develops a multi-agent off-policy actor-critic algorithm using emphatic temporal difference learning.
result Proves convergence of the algorithm under linear function approximation.
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.
The paper develops a method to evaluate recommendation systems without A/B testing.
problem Evaluating new recommendation algorithms efficiently and accurately.
method An estimator that predicts algorithm performance using historical data.
result The estimator converges to true performance at a rate of .
Improves off-policy evaluation weights for balanced state-action pair distribution.
problem Imbalance in importance sampling weights for off-policy evaluation of contextual bandits.
method Balanced Off-Policy Evaluation (B-OPE) method that minimizes imbalance to desired counterfactual distribution of state-action pairs.
result Experimental evidence shows B-OPE improves offline policy evaluation in both discrete and continuous action spaces.
This study improves convergence of two-timescale SA under Markovian noise in reinforcement learning.
problem Stability and convergence of two-timescale stochastic approximations under Markovian noise.
method Introduced a new control strategy for the fast timescale parameter.
result Established almost sure convergence of TDC with eligibility traces under off-policy learning with linear function approximation.
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 . Two novel algorithms are proposed to approximate the true value…
Estimates policy value from off-policy data in contextual bandits.
problem Estimating policy value from limited off-policy data in contextual bandits.
method Empirical likelihood techniques for optimization.
result Improves over previous methods in finite sample regimes.
Hierarchical reinforcement learning (HRL) is a promising approach to extend traditional reinforcement learning (RL) methods to solve more complex tasks. Yet, the majority of current HRL methods require careful task-specific design and on-policy training, making them difficult to apply in real-world scenarios. In this p…
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.
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.
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 …