Problem Decomposition

9 papers with code • 0 benchmarks • 0 datasets

This task has no description! Would you like to contribute one?

Most implemented papers

Meta-Optimizing Semantic Evolutionary Search

opencog/moses Association for Computing Machinery (ACM) 2017

I present MOSES (meta-optimizing semantic evolutionary search), a new probabilistic modeling (estimation of distribution) approach to program evolution.

Decomposition Methods with Deep Corrections for Reinforcement Learning

sisl/AutomotivePOMDPs.jl 6 Feb 2018

In contexts where an agent interacts with multiple entities, utility decomposition can be used to separate the global objective into local tasks considering each individual entity independently.

Learning Reward Machines for Partially Observable Reinforcement Learning

RToroIcarte/lrm NeurIPS 2019

Reward Machines (RMs), originally proposed for specifying problems in Reinforcement Learning (RL), provide a structured, automata-based representation of a reward function that allows an agent to decompose problems into subproblems that can be efficiently learned using off-policy learning.

Fast reinforcement learning with generalized policy updates

deepmind/deepmind-research Proceedings of the National Academy of Sciences 2020

Both strategies considerably reduce the amount of data needed to solve a reinforcement-learning problem.

Distilling Reasoning Capabilities into Smaller Language Models

kumar-shridhar/distiiling-lm 1 Dec 2022

In this work, we propose an alternative reasoning scheme, Socratic CoT, that learns a decomposition of the original problem into a sequence of subproblems and uses it to guide the intermediate reasoning steps.

Comparison of Model-Free and Model-Based Learning-Informed Planning for PointGoal Navigation

yimengli46/bellman_point_goal 17 Dec 2022

In this work, we compare the state-of-the-art Deep Reinforcement Learning based approaches with Partially Observable Markov Decision Process (POMDP) formulation of the point goal navigation problem.

Rolling Horizon based Temporal Decomposition for the Offline Pickup and Delivery Problem with Time Windows

mas-research/rollinghorizon 6 Mar 2023

In smaller problem instances, the baseline approach is as competitive as our framework.

Fast Matrix Multiplication Without Tears: A Constraint Programming Approach

khalil-research/matrix-mult-cp 1 Jun 2023

In this work, we propose a simple yet novel Constraint Programming approach to find non-commutative algorithms for fast matrix multiplication or provide proof of infeasibility otherwise.

Small Language Models Fine-tuned to Coordinate Larger Language Models improve Complex Reasoning

lcs2-iiitd/daslam 21 Oct 2023

Additionally, we show that DaSLaM is not limited by the solver's capabilities as a function of scale; e. g., solver LMs with diverse sizes give significant performance improvement with our solver-agnostic decomposition technique.