English
Related papers

Related papers: Scalable Safety-Critical Policy Evaluation with Ac…

200 papers

One of the key limitations of Molecular Dynamics simulations is the computational intractability of sampling protein conformational landscapes associated with either large system size or long timescales. To overcome this bottleneck, we…

Biomolecules · Quantitative Biology 2018-07-09 Zahra Shamsi , Kevin J. Cheng , Diwakar Shukla

Many real-life dynamical systems change abruptly followed by almost stationary periods. In this paper, we consider streams of data with such abrupt behavior and investigate the problem of tracking their statistical properties in an online…

Methodology · Statistics 2019-01-16 Hugo Lewi Hammer , Anis Yazidi

Off-policy evaluation (OPE) aims to accurately evaluate the performance of counterfactual policies using only offline logged data. Although many estimators have been developed, there is no single estimator that dominates the others, because…

Machine Learning · Computer Science 2023-01-31 Takuma Udagawa , Haruka Kiyohara , Yusuke Narita , Yuta Saito , Kei Tateno

In a wide variety of sequential decision making problems, it can be important to estimate the impact of rare events in order to minimize risk exposure. A popular risk measure is the conditional value-at-risk (CVaR), which is commonly…

Machine Learning · Statistics 2020-12-11 Dylan Troop , Frédéric Godin , Jia Yuan Yu

We introduce adaptive sampling methods for stochastic programs with deterministic constraints. First, we propose and analyze a variant of the stochastic projected gradient method where the sample size used to approximate the reduced…

Optimization and Control · Mathematics 2023-02-07 Florian Beiser , Brendan Keith , Simon Urbainczyk , Barbara Wohlmuth

Enforcing state-wise safety constraints is critical for the application of reinforcement learning (RL) in real-world problems, such as autonomous driving and robot manipulation. However, existing safe RL methods only enforce state-wise…

Machine Learning · Computer Science 2024-10-03 Weiye Zhao , Feihan Li , Yifan Sun , Yujie Wang , Rui Chen , Tianhao Wei , Changliu Liu

Reinforcement learning algorithms rely on exploration to discover new behaviors, which is typically achieved by following a stochastic policy. In continuous control tasks, policies with a Gaussian distribution have been widely adopted.…

Machine Learning · Computer Science 2019-03-28 Dmytro Korenkevych , A. Rupam Mahmood , Gautham Vasan , James Bergstra

Training deep reinforcement learning agents on environments with multiple levels / scenes / conditions from the same task, has become essential for many applications aiming to achieve generalization and domain transfer from simulation to…

Machine Learning · Computer Science 2020-05-26 Jaskirat Singh , Liang Zheng

Sharpness-aware minimization (SAM), which searches for flat minima by min-max optimization, has been shown to be useful in improving model generalization. However, since each SAM update requires computing two gradients, its computational…

Machine Learning · Computer Science 2023-05-01 Weisen Jiang , Hansi Yang , Yu Zhang , James Kwok

Markov decision processes (MDPs) are the defacto frame-work for sequential decision making in the presence ofstochastic uncertainty. A classical optimization criterion forMDPs is to maximize the expected discounted-sum pay-off, which…

Artificial Intelligence · Computer Science 2020-02-28 Tomas Brazdil , Krishnendu Chatterjee , Petr Novotny , Jiri Vahala

Ranking interfaces are everywhere in online platforms. There is thus an ever growing interest in their Off-Policy Evaluation (OPE), aiming towards an accurate performance evaluation of ranking policies using logged data. A de-facto approach…

Machine Learning · Statistics 2023-06-28 Haruka Kiyohara , Masatoshi Uehara , Yusuke Narita , Nobuyuki Shimizu , Yasuo Yamamoto , Yuta Saito

We introduce a sample-efficient method for learning state-dependent stiffness control policies for dexterous manipulation. The ability to control stiffness facilitates safe and reliable manipulation by providing compliance and robustness to…

Robotics · Computer Science 2021-09-16 Mincheol Kim , Scott Niekum , Ashish D. Deshpande

We describe an adaptive Markov chain Monte Carlo method suitable for the estimation of rare failure probabilities in complex probabilistic models. This method, the Accelerated Weight Histogram (AWH) method, has its origin in statistical…

Computation · Statistics 2022-10-27 Jack Lidmar , Johan Spross , John Leander

We study risk-sensitive reinforcement learning in finite discounted MDPs, where a generative model of the MDP is assumed to be available. We consider a family or risk measures called the optimized certainty equivalent (OCE), which includes…

Machine Learning · Computer Science 2026-05-22 Oliver Mortensen , Mohammad Sadegh Talebi

Robust planning in interactive scenarios requires predicting the uncertain future to make risk-aware decisions. Unfortunately, due to long-tail safety-critical events, the risk is often under-estimated by finite-sampling approximations of…

Machine Learning · Computer Science 2023-01-13 Haruki Nishimura , Jean Mercat , Blake Wulfe , Rowan McAllister , Adrien Gaidon

The Off-Policy Evaluation (OPE) problem consists of evaluating the performance of counterfactual policies with data collected by another one. To solve the OPE problem, we resort to estimators, which aim to estimate in the most accurate way…

Machine Learning · Computer Science 2024-11-12 Nicolò Felicioni , Michael Benigni , Maurizio Ferrari Dacrema

An open question in autonomous driving is how best to use simulation to validate the safety of autonomous vehicles. Existing techniques rely on simulated rollouts, which can be inefficient for finding rare failure events, while other…

Robotics · Computer Science 2020-06-29 Anthony Corso , Ritchie Lee , Mykel J. Kochenderfer

In robotics, diffusion models can capture multi-modal trajectories from demonstrations, making them a transformative approach in imitation learning. However, achieving optimal performance following this regiment requires a large-scale…

Ensuring safety is a critical challenge in applying Reinforcement Learning (RL) to real-world scenarios. Constrained Reinforcement Learning (CRL) addresses this by maximizing returns under predefined constraints, typically formulated as the…

Machine Learning · Computer Science 2026-01-21 Shiqing Gao , Yihang Zhou , Shuai Shao , Haoyu Luo , Yiheng Bing , Jiaxin Ding , Luoyi Fu , Xinbing Wang

Coupled human-environment systems are increasingly being understood as complex adaptive systems (CAS), in which micro-level interactions between components lead to emergent behavior. Agent-based models (ABMs) hold great promise for…

Applications · Statistics 2026-02-20 Dylan Munson , Arijit Dey , Simon Mak