cs.LGNov 9, 2026

Simulation-aided Reinforcement Learning with Control Variates

Authors: Omer Hemo, Ido Sefi, Mirco Mutti, Aviv Tamar, Kfir Y. Levy

Organizations: Department of Electrical and Computer Engineering, Technion - Israel Institute of Technology

Abstract

Reinforcement Learning (RL) algorithms often rely on data collected from a target environment, which can be expensive and noisy. Although simulators can generate large amounts of additional data, standard simulation mixing approaches, which directly combine simulated and real experience, can degrade performance due to simulator inaccuracies, especially when they bias the solution away from the optimal policy. We propose a conservative simulation-aided learning method based on control variates, where simulated data is used solely to reduce variance in the learning process rather than directly shaping the learning target. We develop our approach for Policy-Evaluation, which is a fundamental building block of RL algorithms. Then we combine it within the actor-critic framework towards policy improvement, as well as extend it towards offline RL scenarios. Experiments on multiple MuJoCo benchmark tasks demonstrate improvements over standard simulation mixing approaches, highlighting control variates as an effective tool for simulation-aided reinforcement learning.

Figures & tables

Appendix figures & tables7 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Sep 28, 2026

ABC: Advantage-Based Control Variates for Reinforcement Learning with Verifiable Rewards

Recent progress in reinforcement learning with verifiable rewards (RLVR) has highlighted the effectiveness of simple critic-free policy-gradient methods such as Group Relative Policy Optimization (GRPO). In contrast, actor-critic methods rely on learned value functions whose approximation error can introduce bias through commonly used advantage estimators such as temporal-difference error. Motivated by this observation, we revisit trajectory-level control variates through an advantage-value formulation, which we call Advantage-Based Control Variates (ABC). This formulation reveals that the covariance structure is closely related to the return decomposition used in Direct Advantage Estimation (DAE). Finally, we combine ABC with DAE into a single actor-critic algorithm and evaluate it in an offline-to-online RLVR setting, where the critic is first trained on previously collected trajectories and adapted during online learning. On mathematical reasoning tasks, ABC achieves performance competitive with GRPO using substantially fewer online optimization steps.
May 27, 2026

Theoretical Foundations and Effective Algorithms for Policy-Aware Simulator Learning

Model-based reinforcement learning (MBRL) agents typically learn world models by minimizing predictive loss. However, powerful RL optimizers inevitably exploit minor model inaccuracies, leading to simulator exploitation and a reality gap where policies succeed in simulation but fail in the real world. We propose that the objective for learning simulators should be strategic robustness rather than predictive accuracy, and formulate this as a zero-sum minimax game between a model player and an adversarial policy player. We provide a comprehensive theoretical analysis: (1) an online learning guarantee showing the game is learnable with sublinear regret bounds; (2) a tractable critic-based simplification bounding the global policy-value gap by the local critic's loss; and (3) an Error-MDP duality, proving that finding the worst-case policy is formally dual to a standard RL problem where the reward is the one-step critic error. This duality yields a provably convergent active data selection algorithm. Experiments on continuous control tasks demonstrate that our approach reduces prediction error in strategically important regions by 1.51.5-2.2×2.2\times and enables policies trained purely in simulation to match near-optimal real-world performance.
Oct 3, 2026

Exact Fast Batch Simulation for Tabular Reinforcement Learning

Simulation is a fundamental computational primitive in reinforcement learning (RL), yet conventional simulation explicitly generates individual trajectories even when downstream procedures use only aggregate statistics. To address this, we develop an exact fast-simulation framework for finite-horizon tabular Markov decision processes. Our framework has two complementary modes. In direct batch simulation, a batch is represented by its aggregate Markov flow. With sufficient parallel simulation resources, this flow can be obtained by trajectory aggregation; when such simulation is unavailable or costly but the initial state and transition distributions are directly accessible, we instead generate an identically distributed flow through forward Markov-flow sampling without materializing individual trajectories. The latter reduces the simulator-side computational dependence on batch size mm from O(m)O(m) to O(1)O(1). In adaptive batch simulation, when batch length is determined by a data-dependent condition, exact multivariate-hypergeometric splitting recursively refines a candidate Markov flow while preserving the conditional law, reducing the cost dependence on mm from O(m)O(m) to O(log⁡m)O(\log m). Together, these modes accelerate simulation by keeping trajectories aggregated whenever possible and refining flows only when required to locate data-dependent boundaries. The framework applies broadly across simulator-based, offline, and online batch or stage-based RL, as illustrated with representative algorithms from each setting.