Evolutionary Policy Optimization

• URL: http://arxiv.org/abs/2503.19037v1
• Date: Mon, 24 Mar 2025 18:08:54 GMT
• Title: Evolutionary Policy Optimization
• Authors: Jianren Wang, Yifan Su, Abhinav Gupta, Deepak Pathak,
• Abstract summary: Current on-policy methods fail to fully leverage the benefits of parallelized environments.<n>EPO is a novel policy gradient algorithm that combines the strengths of EA and policy gradients.<n>We show that EPO significantly improves performance across diverse and challenging environments.
• Score: 47.30139909878251
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Despite its extreme sample inefficiency, on-policy reinforcement learning has become a fundamental tool in real-world applications. With recent advances in GPU-driven simulation, the ability to collect vast amounts of data for RL training has scaled exponentially. However, studies show that current on-policy methods, such as PPO, fail to fully leverage the benefits of parallelized environments, leading to performance saturation beyond a certain scale. In contrast, Evolutionary Algorithms (EAs) excel at increasing diversity through randomization, making them a natural complement to RL. However, existing EvoRL methods have struggled to gain widespread adoption due to their extreme sample inefficiency. To address these challenges, we introduce Evolutionary Policy Optimization (EPO), a novel policy gradient algorithm that combines the strengths of EA and policy gradients. We show that EPO significantly improves performance across diverse and challenging environments, demonstrating superior scalability with parallelized simulations.

Related papers

• Evolutionary Policy Optimization [9.519528646219054]
  A key challenge in reinforcement learning is managing the exploration-exploitation trade-off without sacrificing sample efficiency. This paper proposes Evolutionary Policy Optimization (EPO), a hybrid algorithm that integrates neuroevolution with policy gradient methods for policy optimization. Experimental results show that EPO improves both policy quality and sample efficiency compared to standard PG and EC methods.
  arXiv  Detail & Related papers  (2025-04-17T01:33:06Z)
• RL-finetuning LLMs from on- and off-policy data with a single algorithm [53.70731390624718]
  We introduce a novel reinforcement learning algorithm (AGRO) for fine-tuning large-language models.<n>AGRO leverages the concept of generation consistency, which states that the optimal policy satisfies the notion of consistency across any possible generation of the model.<n>We derive algorithms that find optimal solutions via the sample-based policy gradient and provide theoretical guarantees on their convergence.
  arXiv  Detail & Related papers  (2025-03-25T12:52:38Z)
• Enhancing Sample Efficiency and Exploration in Reinforcement Learning through the Integration of Diffusion Models and Proximal Policy Optimization [1.631115063641726]
  We propose a framework that enhances PPO algorithms by incorporating a diffusion model to generate high-quality virtual trajectories for offline datasets.<n>Our contributions are threefold: we explore the potential of diffusion models in RL, particularly for offline datasets, extend the application of online RL to offline environments, and experimentally validate the performance improvements of PPO with diffusion models.
  arXiv  Detail & Related papers  (2024-09-02T19:10:32Z)
• SAPG: Split and Aggregate Policy Gradients [37.433915947580076]
  We propose a new on-policy RL algorithm that can effectively leverage large-scale environments by splitting them into chunks and fusing them back together via importance sampling. Our algorithm, termed SAPG, shows significantly higher performance across a variety of challenging environments where vanilla PPO and other strong baselines fail to achieve high performance.
  arXiv  Detail & Related papers  (2024-07-29T17:59:50Z)
• Diffusion-based Reinforcement Learning via Q-weighted Variational Policy Optimization [55.97310586039358]
  Diffusion models have garnered widespread attention in Reinforcement Learning (RL) for their powerful expressiveness and multimodality.<n>We propose a novel model-free diffusion-based online RL algorithm, Q-weighted Variational Policy Optimization (QVPO)<n>Specifically, we introduce the Q-weighted variational loss, which can be proved to be a tight lower bound of the policy objective in online RL under certain conditions.<n>We also develop an efficient behavior policy to enhance sample efficiency by reducing the variance of the diffusion policy during online interactions.
  arXiv  Detail & Related papers  (2024-05-25T10:45:46Z)
• Statistically Efficient Variance Reduction with Double Policy Estimation for Off-Policy Evaluation in Sequence-Modeled Reinforcement Learning [53.97273491846883]
  We propose DPE: an RL algorithm that blends offline sequence modeling and offline reinforcement learning with Double Policy Estimation. We validate our method in multiple tasks of OpenAI Gym with D4RL benchmarks.
  arXiv  Detail & Related papers  (2023-08-28T20:46:07Z)
• Diverse Policy Optimization for Structured Action Space [59.361076277997704]
  We propose Diverse Policy Optimization (DPO) to model the policies in structured action space as the energy-based models (EBM) A novel and powerful generative model, GFlowNet, is introduced as the efficient, diverse EBM-based policy sampler. Experiments on ATSC and Battle benchmarks demonstrate that DPO can efficiently discover surprisingly diverse policies.
  arXiv  Detail & Related papers  (2023-02-23T10:48:09Z)
• Evolutionary Action Selection for Gradient-based Policy Learning [6.282299638495976]
  Evolutionary algorithms (EAs) and Deep Reinforcement Learning (DRL) have recently been combined to integrate the advantages of the two solutions for better policy learning. We propose Evolutionary Action Selection-Twin Delayed Deep Deterministic Policy Gradient (EAS-TD3), a novel combination of EA and DRL.
  arXiv  Detail & Related papers  (2022-01-12T03:31:21Z)
• Semi-On-Policy Training for Sample Efficient Multi-Agent Policy Gradients [51.749831824106046]
  We introduce semi-on-policy (SOP) training as an effective and computationally efficient way to address the sample inefficiency of on-policy policy gradient methods. We show that our methods perform as well or better than state-of-the-art value-based methods on a variety of SMAC tasks.
  arXiv  Detail & Related papers  (2021-04-27T19:37:01Z)

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.