Domain-Independent Dynamic Programming

• URL: http://arxiv.org/abs/2401.13883v2
• Date: Fri, 31 May 2024 21:05:34 GMT
• Title: Domain-Independent Dynamic Programming
• Authors: Ryo Kuroiwa, J. Christopher Beck,
• Abstract summary: Domain-independent dynamic programming (DIDP) is a new model-based paradigm based on dynamic programming (DP) We introduce Dynamic Programming Description Language (DyPDL), a formalism to define DP models based on a state transition system, inspired by AI planning. We show that search algorithms can be used to solve DyPDL models and propose seven DIDP solvers.
• Score: 5.449167190254984
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: For combinatorial optimization problems, model-based paradigms such as mixed-integer programming (MIP) and constraint programming (CP) aim to decouple modeling and solving a problem: the `holy grail' of declarative problem solving. We propose domain-independent dynamic programming (DIDP), a new model-based paradigm based on dynamic programming (DP). While DP is not new, it has typically been implemented as a problem-specific method. We introduce Dynamic Programming Description Language (DyPDL), a formalism to define DP models based on a state transition system, inspired by AI planning. We show that heuristic search algorithms can be used to solve DyPDL models and propose seven DIDP solvers. We experimentally compare our DIDP solvers with commercial MIP and CP solvers (solving MIP and CP models, respectively) on common benchmark instances of eleven combinatorial optimization problem classes. We show that DIDP outperforms MIP in nine problem classes, CP also in nine problem classes, and both MIP and CP in seven.

Related papers

• Q-learning for Quantile MDPs: A Decomposition, Performance, and Convergence Analysis [30.713243690224207]
  In Markov decision processes (MDPs), quantile risk measures such as Value-at-Risk are a standard metric for modeling RL agents' preferences for certain outcomes. This paper proposes a new Q-learning algorithm for quantile optimization in MDPs with strong convergence and performance guarantees.
  arXiv  Detail & Related papers  (2024-10-31T16:53:20Z)
• Enhancing Multi-Step Reasoning Abilities of Language Models through Direct Q-Function Optimization [50.485788083202124]
  Reinforcement Learning (RL) plays a crucial role in aligning large language models with human preferences and improving their ability to perform complex tasks. We introduce Direct Q-function Optimization (DQO), which formulates the response generation process as a Markov Decision Process (MDP) and utilizes the soft actor-critic (SAC) framework to optimize a Q-function directly parameterized by the language model. Experimental results on two math problem-solving datasets, GSM8K and MATH, demonstrate that DQO outperforms previous methods, establishing it as a promising offline reinforcement learning approach for aligning language models.
  arXiv  Detail & Related papers  (2024-10-11T23:29:20Z)
• MDP Geometry, Normalization and Value Free Solvers [15.627546283580166]
  The Markov Decision Process (MDP) is a widely used mathematical model for sequential decision-making problems. We show that MDPs can be divided into equivalence classes with indistinguishable key solving algorithms dynamics.
  arXiv  Detail & Related papers  (2024-07-09T09:39:45Z)
• Solving Multi-Model MDPs by Coordinate Ascent and Dynamic Programming [8.495921422521068]
  Multi-model Markov decision process (MMDP) is a promising framework for computing policies. MMDPs aim to find a policy that maximizes the expected return over a distribution of MDP models. We propose CADP, which combines a coordinate ascent method and a dynamic programming algorithm for solving MMDPs.
  arXiv  Detail & Related papers  (2024-07-08T18:47:59Z)
• Efficient Adaptation in Mixed-Motive Environments via Hierarchical Opponent Modeling and Planning [51.52387511006586]
  We propose Hierarchical Opponent modeling and Planning (HOP), a novel multi-agent decision-making algorithm. HOP is hierarchically composed of two modules: an opponent modeling module that infers others' goals and learns corresponding goal-conditioned policies. HOP exhibits superior few-shot adaptation capabilities when interacting with various unseen agents, and excels in self-play scenarios.
  arXiv  Detail & Related papers  (2024-06-12T08:48:06Z)
• Sample Complexity Characterization for Linear Contextual MDPs [67.79455646673762]
  Contextual decision processes (CMDPs) describe a class of reinforcement learning problems in which the transition kernels and reward functions can change over time with different MDPs indexed by a context variable. CMDPs serve as an important framework to model many real-world applications with time-varying environments. We study CMDPs under two linear function approximation models: Model I with context-varying representations and common linear weights for all contexts; and Model II with common representations for all contexts and context-varying linear weights.
  arXiv  Detail & Related papers  (2024-02-05T03:25:04Z)
• Domain-Independent Dynamic Programming: Generic State Space Search for Combinatorial Optimization [13.386517072025722]
  We propose domain-independent dynamic programming (DIDP), a new model-based paradigm based on dynamic programming (DP) We propose Dynamic Programming Description Language (DyPDL), a formalism to define DP models, and develop Cost-Algebraic A* Solver for DyP (CAASDy)
  arXiv  Detail & Related papers  (2022-11-26T00:15:45Z)
• Multi-Objective Policy Gradients with Topological Constraints [108.10241442630289]
  We present a new algorithm for a policy gradient in TMDPs by a simple extension of the proximal policy optimization (PPO) algorithm. We demonstrate this on a real-world multiple-objective navigation problem with an arbitrary ordering of objectives both in simulation and on a real robot.
  arXiv  Detail & Related papers  (2022-09-15T07:22:58Z)
• Neural Stochastic Dual Dynamic Programming [99.80617899593526]
  We introduce a trainable neural model that learns to map problem instances to a piece-wise linear value function. $nu$-SDDP can significantly reduce problem solving cost without sacrificing solution quality.
  arXiv  Detail & Related papers  (2021-12-01T22:55:23Z)
• Deep Policy Dynamic Programming for Vehicle Routing Problems [89.96386273895985]
  We propose Deep Policy Dynamic Programming (D PDP) to combine the strengths of learned neurals with those of dynamic programming algorithms. D PDP prioritizes and restricts the DP state space using a policy derived from a deep neural network, which is trained to predict edges from example solutions. We evaluate our framework on the travelling salesman problem (TSP) and the vehicle routing problem (VRP) and show that the neural policy improves the performance of (restricted) DP algorithms.
  arXiv  Detail & Related papers  (2021-02-23T15:33:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.