Instance Selection for Dynamic Algorithm Configuration with Reinforcement Learning: Improving Generalization

• URL: http://arxiv.org/abs/2407.13513v1
• Date: Thu, 18 Jul 2024 13:44:43 GMT
• Title: Instance Selection for Dynamic Algorithm Configuration with Reinforcement Learning: Improving Generalization
• Authors: Carolin Benjamins, Gjorgjina Cenikj, Ana Nikolikj, Aditya Mohan, Tome Eftimov, Marius Lindauer,
• Abstract summary: Dynamic Algorithm configuration (DAC) addresses the challenge of dynamically setting hyperparameters of an algorithm for a diverse set of instances. Agents trained with Deep Reinforcement Learning (RL) offer a pathway to solve such settings. We take a step towards mitigating this by selecting a representative subset of training instances to overcome overrepresentation and then retraining the agent on this subset to improve its generalization performance.
• Score: 16.49696895887536
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Dynamic Algorithm Configuration (DAC) addresses the challenge of dynamically setting hyperparameters of an algorithm for a diverse set of instances rather than focusing solely on individual tasks. Agents trained with Deep Reinforcement Learning (RL) offer a pathway to solve such settings. However, the limited generalization performance of these agents has significantly hindered the application in DAC. Our hypothesis is that a potential bias in the training instances limits generalization capabilities. We take a step towards mitigating this by selecting a representative subset of training instances to overcome overrepresentation and then retraining the agent on this subset to improve its generalization performance. For constructing the meta-features for the subset selection, we particularly account for the dynamic nature of the RL agent by computing time series features on trajectories of actions and rewards generated by the agent's interaction with the environment. Through empirical evaluations on the Sigmoid and CMA-ES benchmarks from the standard benchmark library for DAC, called DACBench, we discuss the potentials of our selection technique compared to training on the entire instance set. Our results highlight the efficacy of instance selection in refining DAC policies for diverse instance spaces.

Related papers

• ODRL: A Benchmark for Off-Dynamics Reinforcement Learning [59.72217833812439]
  We introduce ODRL, the first benchmark tailored for evaluating off-dynamics RL methods. ODRL contains four experimental settings where the source and target domains can be either online or offline. We conduct extensive benchmarking experiments, which show that no method has universal advantages across varied dynamics shifts.
  arXiv  Detail & Related papers  (2024-10-28T05:29:38Z)
• Causal Coordinated Concurrent Reinforcement Learning [8.654978787096807]
  We propose a novel algorithmic framework for data sharing and coordinated exploration for the purpose of learning more data-efficient and better performing policies under a concurrent reinforcement learning setting. Our algorithm leverages a causal inference algorithm in the form of Additive Noise Model - Mixture Model (ANM-MM) in extracting model parameters governing individual differentials via independence enforcement. We propose a new data sharing scheme based on a similarity measure of the extracted model parameters and demonstrate superior learning speeds on a set of autoregressive, pendulum and cart-pole swing-up tasks.
  arXiv  Detail & Related papers  (2024-01-31T17:20:28Z)
• Quantifying Agent Interaction in Multi-agent Reinforcement Learning for Cost-efficient Generalization [63.554226552130054]
  Generalization poses a significant challenge in Multi-agent Reinforcement Learning (MARL) The extent to which an agent is influenced by unseen co-players depends on the agent's policy and the specific scenario. We present the Level of Influence (LoI), a metric quantifying the interaction intensity among agents within a given scenario and environment.
  arXiv  Detail & Related papers  (2023-10-11T06:09:26Z)
• Inferring Preferences from Demonstrations in Multi-objective Reinforcement Learning: A Dynamic Weight-based Approach [0.0]
  In multi-objective decision-making, preference inference is the process of inferring the preferences of a decision-maker for different objectives. This research proposes a Dynamic Weight-based Preference Inference algorithm that can infer the preferences of agents acting in multi-objective decision-making problems.
  arXiv  Detail & Related papers  (2023-04-27T11:55:07Z)
• Multi-agent Dynamic Algorithm Configuration [29.065510165544865]
  Automated algorithm configuration relieves users from tedious, trial-and-error tuning tasks. In this paper, we propose multi-agent DAC (MA-DAC) for complex algorithms. We show that MA-DAC achieves superior performance compared with other configuration tuning approaches.
  arXiv  Detail & Related papers  (2022-10-13T08:39:32Z)
• DACBench: A Benchmark Library for Dynamic Algorithm Configuration [30.217571636151295]
  We propose DACBench, a benchmark library that seeks to collect and standardize existing DAC benchmarks from different AI domains. To show the potential, broad applicability and challenges of DAC, we explore how a set of six initial benchmarks compare in several dimensions of difficulty.
  arXiv  Detail & Related papers  (2021-05-18T14:16:51Z)
• Learning to Continuously Optimize Wireless Resource in a Dynamic Environment: A Bilevel Optimization Perspective [52.497514255040514]
  This work develops a new approach that enables data-driven methods to continuously learn and optimize resource allocation strategies in a dynamic environment. We propose to build the notion of continual learning into wireless system design, so that the learning model can incrementally adapt to the new episodes. Our design is based on a novel bilevel optimization formulation which ensures certain fairness" across different data samples.
  arXiv  Detail & Related papers  (2021-05-03T07:23:39Z)
• Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning [83.66080019570461]
  We propose two environment-agnostic, algorithm-agnostic quantitative metrics for task difficulty. We show that these metrics have higher correlations with normalized task solvability scores than a variety of alternatives. These metrics can also be used for fast and compute-efficient optimizations of key design parameters.
  arXiv  Detail & Related papers  (2021-03-23T17:49:50Z)
• Instance based Generalization in Reinforcement Learning [24.485597364200824]
  We analyze policy learning in the context of Partially Observable Markov Decision Processes (POMDPs) We prove that, independently of the exploration strategy, reusing instances introduces significant changes on the effective Markov dynamics the agent observes during training. We propose training a shared belief representation over an ensemble of specialized policies, from which we compute a consensus policy that is used for data collection, disallowing instance specific exploitation.
  arXiv  Detail & Related papers  (2020-11-02T16:19:44Z)
• Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinforcement Learning [137.39196753245105]
  We present a new model-based reinforcement learning algorithm that learns a multi-headed dynamics model for dynamics generalization. We incorporate context learning, which encodes dynamics-specific information from past experiences into the context latent vector. Our method exhibits superior zero-shot generalization performance across a variety of control tasks, compared to state-of-the-art RL methods.
  arXiv  Detail & Related papers  (2020-10-26T03:20:42Z)
• Dynamic Divide-and-Conquer Adversarial Training for Robust Semantic Segmentation [79.42338812621874]
  Adversarial training is promising for improving robustness of deep neural networks towards adversarial perturbations. We formulate a general adversarial training procedure that can perform decently on both adversarial and clean samples. We propose a dynamic divide-and-conquer adversarial training (DDC-AT) strategy to enhance the defense effect.
  arXiv  Detail & Related papers  (2020-03-14T05:06:49Z)

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.