English
Related papers

Related papers: Path Integral Policy Improvement with Covariance M…

200 papers

Recently, a novel class of Approximate Policy Iteration (API) algorithms have demonstrated impressive practical performance (e.g., ExIt from [2], AlphaGo-Zero from [27]). This new family of algorithms maintains, and alternately optimizes,…

Machine Learning · Computer Science 2019-04-09 Wen Sun , Geoffrey J. Gordon , Byron Boots , J. Andrew Bagnell

When faced with a specific optimization problem, choosing which algorithm to use is always a tough task. Not only is there a vast variety of algorithms to select from, but these algorithms often are controlled by many hyperparameters, which…

Neural and Evolutionary Computing · Computer Science 2020-01-07 Diederick Vermetten , Hao Wang , Carola Doerr , Thomas Bäck

Relational Markov Decision Processes are a useful abstraction for complex reinforcement learning problems and stochastic planning problems. Recent work developed representation schemes and algorithms for planning in such problems using the…

Artificial Intelligence · Computer Science 2012-06-26 Chenggang Wang , Roni Khardon

The development of Policy Iteration (PI) has inspired many recent algorithms for Reinforcement Learning (RL), including several policy gradient methods that gained both theoretical soundness and empirical success on a variety of tasks. The…

Machine Learning · Computer Science 2025-06-03 Zhijie Xie , Shenghui Song

The Covariance Matrix Adaptation Evolution Strategy (CMA-ES) is a popular method to deal with nonconvex and/or stochastic optimization problems when the gradient information is not available. Being based on the CMA-ES, the recently proposed…

Neural and Evolutionary Computing · Computer Science 2017-05-19 Ilya Loshchilov , Tobias Glasmachers , Hans-Georg Beyer

Continual learning systems face the dual challenge of preventing catastrophic forgetting while maintaining energy efficiency, particularly in resource-constrained environments. This paper introduces Pathway-based Progressive Inference…

Machine Learning · Computer Science 2025-06-24 Suyash Gaurav , Jukka Heikkonen , Jatin Chaudhary

Policy gradient methods are powerful reinforcement learning algorithms and have been demonstrated to solve many complex tasks. However, these methods are also data-inefficient, afflicted with high variance gradient estimates, and frequently…

Machine Learning · Computer Science 2019-05-15 Andreas Doerr , Michael Volpp , Marc Toussaint , Sebastian Trimpe , Christian Daniel

Consider the problem of approximating the optimal policy of a Markov decision process (MDP) by sampling state transitions. In contrast to existing reinforcement learning methods that are based on successive approximations to the nonlinear…

Machine Learning · Computer Science 2017-10-18 Mengdi Wang

Policy Mirror Descent (PMD) is a general family of algorithms that covers a wide range of novel and fundamental methods in reinforcement learning. Motivated by the instability of policy iteration (PI) with inexact policy evaluation, PMD…

Optimization and Control · Mathematics 2023-11-23 Emmeran Johnson , Ciara Pike-Burke , Patrick Rebeschini

The famous Policy Iteration algorithm alternates between policy improvement and policy evaluation. Implementations of this algorithm with several variants of the latter evaluation stage, e.g, $n$-step and trace-based returns, have been…

Artificial Intelligence · Computer Science 2018-08-01 Yonathan Efroni , Gal Dalal , Bruno Scherrer , Shie Mannor

Multi-objective reinforcement learning (MORL) algorithms tackle sequential decision problems where agents may have different preferences over (possibly conflicting) reward functions. Such algorithms often learn a set of policies (each…

Machine Learning · Computer Science 2023-08-16 Lucas N. Alegre , Ana L. C. Bazzan , Diederik M. Roijers , Ann Nowé , Bruno C. da Silva

In this paper we investigate the convergence properties of a variant of the Covariance Matrix Adaptation Evolution Strategy (CMA-ES). Our study is based on the recent theoretical foundation that the pure rank-mu update CMA-ES performs the…

Artificial Intelligence · Computer Science 2017-06-20 Youhei Akimoto

Exploration is essential in reinforcement learning as an agent relies on trial and error to learn an optimal policy. However, when rewards are sparse, naive exploration strategies, like noise injection, are often insufficient. Intrinsic…

Machine Learning · Computer Science 2026-01-30 Minjae Cho , Huy Trong Tran

Direct policy optimization in reinforcement learning is usually solved with policy-gradient algorithms, which optimize policy parameters via stochastic gradient ascent. This paper provides a new theoretical interpretation and justification…

Machine Learning · Computer Science 2023-10-24 Adrien Bolland , Gilles Louppe , Damien Ernst

Reinforcement Learning with Verifiable Rewards (RLVR) enhances Large Language Model (LLM) reasoning but suffers from advantage collapse on ``hard samples'' where all rollouts fail. This lack of variance eliminates crucial learning signals.…

Machine Learning · Computer Science 2026-05-08 Xinyu Lu , Kaiqi Zhang , Jinglin Yang , Boxi Cao , Yaojie Lu , Hongyu Lin , Min He , Xianpei Han , Le Sun

The posterior in probabilistic programs with stochastic support decomposes as a weighted sum of the local posterior distributions associated with each possible program path. We show that making predictions with this full posterior…

Machine Learning · Computer Science 2024-04-15 Tim Reichelt , Luke Ong , Tom Rainforth

How do statistical dependencies in measurement noise influence high-dimensional inference? To answer this, we study the paradigmatic spiked matrix model of principal components analysis (PCA), where a rank-one matrix is corrupted by…

Information Theory · Computer Science 2023-06-05 Jean Barbier , Francesco Camilli , Marco Mondelli , Manuel Saenz

Covariance selection seeks to estimate a covariance matrix by maximum likelihood while restricting the number of nonzero inverse covariance matrix coefficients. A single penalty parameter usually controls the tradeoff between log likelihood…

Optimization and Control · Mathematics 2010-10-12 Vijay Krishnamurthy , Alexandre d'Aspremont

Reinforcement learning of real-world tasks is very data inefficient, and extensive simulation-based modelling has become the dominant approach for training systems. However, in human-robot interaction and many other real-world settings,…

Machine Learning · Computer Science 2023-09-12 Nat Wannawas , A. Aldo Faisal

Various variants of the well known Covariance Matrix Adaptation Evolution Strategy (CMA-ES) have been proposed recently, which improve the empirical performance of the original algorithm by structural modifications. However, in practice it…

Neural and Evolutionary Computing · Computer Science 2018-08-20 Sander van Rijn , Hao Wang , Matthijs van Leeuwen , Thomas Bäck