Ancestral Reinforcement Learning: Unifying Zeroth-Order Optimization and Genetic Algorithms for Reinforcement Learning

• URL: http://arxiv.org/abs/2408.09493v2
• Date: Mon, 2 Sep 2024 16:19:25 GMT
• Title: Ancestral Reinforcement Learning: Unifying Zeroth-Order Optimization and Genetic Algorithms for Reinforcement Learning
• Authors: So Nakashima, Tetsuya J. Kobayashi,
• Abstract summary: Ancestral Reinforcement Learning (ARL) combines the robust gradient estimation of ZOO with the exploratory power of Genetic Algorithms. We theoretically reveal that the populational search in ARL implicitly induces the KL-regularization of the objective function, resulting in the enhanced exploration.
• Score: 0.8287206589886879
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement Learning (RL) offers a fundamental framework for discovering optimal action strategies through interactions within unknown environments. Recent advancement have shown that the performance and applicability of RL can significantly be enhanced by exploiting a population of agents in various ways. Zeroth-Order Optimization (ZOO) leverages an agent population to estimate the gradient of the objective function, enabling robust policy refinement even in non-differentiable scenarios. As another application, Genetic Algorithms (GA) boosts the exploration of policy landscapes by mutational generation of policy diversity in an agent population and its refinement by selection. A natural question is whether we can have the best of two worlds that the agent population can have. In this work, we propose Ancestral Reinforcement Learning (ARL), which synergistically combines the robust gradient estimation of ZOO with the exploratory power of GA. The key idea in ARL is that each agent within a population infers gradient by exploiting the history of its ancestors, i.e., the ancestor population in the past, while maintaining the diversity of policies in the current population as in GA. We also theoretically reveal that the populational search in ARL implicitly induces the KL-regularization of the objective function, resulting in the enhanced exploration. Our results extend the applicability of populational algorithms for RL.

Related papers

• Agentic Reinforced Policy Optimization [66.96989268893932]
  Large-scale reinforcement learning with verifiable rewards (RLVR) has demonstrated its effectiveness in harnessing the potential of large language models (LLMs) for single-turn reasoning tasks.<n>Current RL algorithms inadequately balance the models' intrinsic long-horizon reasoning capabilities and their proficiency in multi-turn tool interactions.<n>We propose Agentic Reinforced Policy Optimization (ARPO), a novel agentic RL algorithm tailored for training multi-turn LLM-based agents.
  arXiv  Detail & Related papers  (2025-07-26T07:53:11Z)
• Synergizing Reinforcement Learning and Genetic Algorithms for Neural Combinatorial Optimization [25.633698252033756]
  We propose the Evolutionary Augmentation Mechanism (EAM) to synergize the learning efficiency of DRL with the global search power of GAs.<n>EAM operates by generating solutions from a learned policy and refining them through domain-specific genetic operations such as crossover and mutation.<n>EAM can be seamlessly integrated with state-of-the-art DRL solvers such as the Attention Model, POMO, and SymNCO.
  arXiv  Detail & Related papers  (2025-06-11T05:17:30Z)
• GenPO: Generative Diffusion Models Meet On-Policy Reinforcement Learning [34.25769740497309]
  GenPO is a generative policy optimization framework that leverages exact diffusion inversion to construct invertible action mappings.<n>GenPO is the first method to successfully integrate diffusion policies into on-policy RL, unlocking their potential for large-scale parallelized training and real-world robotic deployment.
  arXiv  Detail & Related papers  (2025-05-24T15:57:07Z)
• Global Reinforcement Learning: Beyond Linear and Convex Rewards via Submodular Semi-gradient Methods [42.04223902155739]
  We introduce Global RL (GRL), where rewards are globally defined over trajectories instead of locally over states. By exploiting ideas from submodular optimization, we propose a novel algorithmic scheme that converts any GRL problem to a sequence of classic RL problems.
  arXiv  Detail & Related papers  (2024-07-13T14:45:08Z)
• How Can LLM Guide RL? A Value-Based Approach [68.55316627400683]
  Reinforcement learning (RL) has become the de facto standard practice for sequential decision-making problems by improving future acting policies with feedback. Recent developments in large language models (LLMs) have showcased impressive capabilities in language understanding and generation, yet they fall short in exploration and self-improvement capabilities. We develop an algorithm named LINVIT that incorporates LLM guidance as a regularization factor in value-based RL, leading to significant reductions in the amount of data needed for learning.
  arXiv  Detail & Related papers  (2024-02-25T20:07:13Z)
• Reinforcement Learning-assisted Evolutionary Algorithm: A Survey and Research Opportunities [63.258517066104446]
  Reinforcement learning integrated as a component in the evolutionary algorithm has demonstrated superior performance in recent years. We discuss the RL-EA integration method, the RL-assisted strategy adopted by RL-EA, and its applications according to the existing literature. In the applications of RL-EA section, we also demonstrate the excellent performance of RL-EA on several benchmarks and a range of public datasets.
  arXiv  Detail & Related papers  (2023-08-25T15:06:05Z)
• Proximal Policy Gradient Arborescence for Quality Diversity Reinforcement Learning [14.16864939687988]
  Training generally capable agents that thoroughly explore their environment and learn new and diverse skills is a long-term goal of robot learning. Quality Diversity Reinforcement Learning (QD-RL) is an emerging research area that blends the best aspects of both fields.
  arXiv  Detail & Related papers  (2023-05-23T08:05:59Z)
• Supplementing Gradient-Based Reinforcement Learning with Simple Evolutionary Ideas [4.873362301533824]
  We present a simple, sample-efficient algorithm for introducing large but directed learning steps in reinforcement learning (RL) The methodology uses a population of RL agents training with a common experience buffer, with occasional crossovers and mutations of the agents in order to search efficiently through the policy space.
  arXiv  Detail & Related papers  (2023-05-10T09:46:53Z)
• One-Step Distributional Reinforcement Learning [10.64435582017292]
  We present the simpler one-step distributional reinforcement learning (OS-DistrRL) framework. We show that our approach comes with a unified theory for both policy evaluation and control. We propose two OS-DistrRL algorithms for which we provide an almost sure convergence analysis.
  arXiv  Detail & Related papers  (2023-04-27T06:57:00Z)
• Reinforcement Learning from Diverse Human Preferences [68.4294547285359]
  This paper develops a method for crowd-sourcing preference labels and learning from diverse human preferences. The proposed method is tested on a variety of tasks in DMcontrol and Meta-world. It has shown consistent and significant improvements over existing preference-based RL algorithms when learning from diverse feedback.
  arXiv  Detail & Related papers  (2023-01-27T15:18:54Z)
• Flexible Attention-Based Multi-Policy Fusion for Efficient Deep Reinforcement Learning [78.31888150539258]
  Reinforcement learning (RL) agents have long sought to approach the efficiency of human learning. Prior studies in RL have incorporated external knowledge policies to help agents improve sample efficiency. We present Knowledge-Grounded RL (KGRL), an RL paradigm fusing multiple knowledge policies and aiming for human-like efficiency and flexibility.
  arXiv  Detail & Related papers  (2022-10-07T17:56:57Z)
• A reinforcement learning approach to resource allocation in genomic selection [11.369433574169994]
  We develop a reinforcement learning-based algorithm to automatically learn to allocate limited resources across different generations of breeding. We demonstrate the effectiveness of the proposed method in enhancing genetic gain using a case study with realistic data.
  arXiv  Detail & Related papers  (2021-07-22T19:55:16Z)
• Variational Empowerment as Representation Learning for Goal-Based Reinforcement Learning [114.07623388322048]
  We discuss how the standard goal-conditioned RL (GCRL) is encapsulated by the objective variational empowerment. Our work lays a novel foundation from which to evaluate, analyze, and develop representation learning techniques in goal-based RL.
  arXiv  Detail & Related papers  (2021-06-02T18:12:26Z)
• Learning Sampling Policy for Faster Derivative Free Optimization [100.27518340593284]
  We propose a new reinforcement learning based ZO algorithm (ZO-RL) with learning the sampling policy for generating the perturbations in ZO optimization instead of using random sampling. Our results show that our ZO-RL algorithm can effectively reduce the variances of ZO gradient by learning a sampling policy, and converge faster than existing ZO algorithms in different scenarios.
  arXiv  Detail & Related papers  (2021-04-09T14:50:59Z)

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.