在资源受限下，如何分配记忆影响强化学习性能。
Memory Allocation in Resource-Constrained Reinforcement Learning
- 研究记忆分配对智能体内部过程的影响。
- 不同内存分配显著改变MCTS和DQN的性能表现。
- 适合关注边缘设备上强化学习优化的研究者。
资源约束会从根本上改变学习与决策过程。本文探讨在使用标准强化学习算法探索未知环境时，记忆限制如何影响智能体的表现。具体而言，记忆受限的智能体面临一个困境：应将有限的内存分配给世界模型估计，还是用于基于该模型制定计划？我们针对基于MCTS和DQN的算法研究这一问题，并考察在阶段性与持续学习设置中，不同内存分配策略对性能的影响。
原文摘要 · Abstract (English)
Resource constraints can fundamentally change both learning and decision-making. We explore how memory constraints influence an agent's performance when navigating unknown environments using standard reinforcement learning algorithms. Specifically, memory-constrained agents face a dilemma: how much of their limited memory should be allocated to each of the agent's internal processes, such as estimating a world model, as opposed to forming a plan using that model? We study this dilemma in MCTS- and DQN-based algorithms and examine how different allocations of memory impact performance in episodic and continual learning settings.
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。