用哈达玛积最大池化提升强化学习性能，突破传统网络结构限制。
Hadamax Encoding: Elevating Performance in Model-Free Atari
- 通过并行层的GELU激活后做哈达玛积再最大池化，设计新型编码器。
- 在Atari-57上比基础PQN提升80%性能，超越Rainbow-DQN。
- 适合关注强化学习模型架构创新的研究者和开发者。
神经网络架构对机器学习影响巨大。在强化学习中，网络结构长期保持简单，因改动常仅带来微小性能提升。本文提出一种面向像素输入的无模型强化学习新型编码器——Hadamax（Hadamard max-pooling）。该编码器通过在GELU激活的并行隐藏层之间进行哈达玛积运算，再进行最大池化，实现状态表征。基于最新PQN算法，Hadamax-PQN在Atari-57基准测试中达到当前最优性能。无需调整任何算法超参数，其性能较原始PQN提升80%，显著优于Rainbow-DQN。代码已开源，便于复现。
原文摘要 · Abstract (English)
Neural network architectures have a large impact in machine learning. In reinforcement learning, network architectures have remained notably simple, as changes often lead to small gains in performance. This work introduces a novel encoder architecture for pixel-based model-free reinforcement learning. The Hadamax (\textbf{Hada}mard \textbf{max}-pooling) encoder achieves state-of-the-art performance by max-pooling Hadamard products between GELU-activated parallel hidden layers. Based on the recent PQN algorithm, the Hadamax encoder achieves state-of-the-art model-free performance in the Atari-57 benchmark. Specifically, without applying any algorithmic hyperparameter modifications, Hadamax-PQN achieves an 80\% performance gain over vanilla PQN and significantly surpasses Rainbow-DQN. For reproducibility, the full code is available on \href{https://github.com/Jacobkooi/Hadamax}{GitHub}.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。