paper-with-me

Papers

Monte Carlo Policy Gradient Method for Binary Optimization

2023-07-03 · Cheng Chen, Ruitao Chen, Tianyou Li, Ruichen Ao, Zaiwen Wen

Binary optimization has a wide range of applications in combinatorial optimization problems such as MaxCut, MIMO detection, and MaxSAT. However, these problems are typically NP-hard due to the binary constraints. We develop a novel probabilistic model to sample the binary solution according to a parameterized policy distribution. Specifically, minimizing the KL divergence between the parameterized policy distribution and the Gibbs distributions of the function value leads to a stochastic optimization problem whose policy gradient can be derived explicitly similar to reinforcement learning. For coherent exploration in discrete spaces, parallel Markov Chain Monte Carlo (MCMC) methods are employed to sample from the policy distribution with diversity and approximate the gradient efficiently. We further develop a filter scheme to replace the original objective function by the one with the local search technique to broaden the horizon of the function landscape. Convergence to stationary points in expectation of the policy gradient method is established based on the concentration inequality for MCMC. Numerical results show that this framework is very promising to provide near-optimal solutions for quite a few binary optimization problems.

📄 PDF Abstract BibTeX arXiv:2307.00783

Code (1)

optsuite/mcpg 공식 구현 pytorch

Tasks

Combinatorial OptimizationDiversityStochastic Optimization

Similar Papers 제목 키워드 기반

Monte-Carlo Tree Search for Policy Optimization

2019-12-23 · Xiaobai Ma, Katherine Driggs-Campbell, Zongzhang Zhang, Mykel J. Kochenderfer

Gradient-based methods are often used for policy optimization in deep reinforcement learning, despite being vulnerable to local optima and saddle points. Although gradient-free methods (e.g., genetic algorithms or evolut…

Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Policy Learning and Evaluation with Randomized Quasi-Monte Carlo

2022-02-16 · Sebastien M. R. Arnold, Pierre L'Ecuyer, Liyu Chen, Yi-fan Chen 외

Reinforcement learning constantly deals with hard integrals, for example when computing expectations in policy evaluation and policy iteration. These integrals are rarely analytically solvable and typically estimated wit…

continuous-controlContinuous ControlPolicy Gradient MethodsReinforcement Learning (RL)

Deep Bayesian Quadrature Policy Optimization

2020-06-28 · Akella Ravi Tej, Kamyar Azizzadenesheli, Mohammad Ghavamzadeh, Anima Anandkumar 외

We study the problem of obtaining accurate policy gradient estimates using a finite number of samples. Monte-Carlo methods have been the default choice for policy gradient estimation, despite suffering from high variance…

continuous-controlContinuous ControlPolicy Gradient Methods

Markov Chain Monte Carlo Policy Optimization

2021-01-04 · Daniel Hsu

Discovering approximately optimal policies in domains is crucial to applying reinforcement learning (RL) in many real-world scenarios, which is termed as policy optimization. By viewing the policy optimization from the p…

continuous-controlContinuous Controlreinforcement-learningReinforcement Learning (RL)+1

Adaptive Correlated Monte Carlo for Contextual Categorical Sequence Generation

2019-12-31 · ICLR 2020 1 · Xinjie Fan, Yizhe Zhang, Zhendong Wang, Mingyuan Zhou

Sequence generation models are commonly refined with reinforcement learning over user-defined metrics. However, high gradient variance hinders the practical use of this method. To stabilize this method, we adapt to conte…

Image CaptioningProgram SynthesisReinforcement Learning