首个专为强化学习可塑性优化设计的开源框架，解决模型终身学习中的适应力退化问题。
Plasticine: Accelerating Research in Plasticity-Motivated Deep Reinforcement Learning
- 提供13种可塑性缓解方法的单文件实现，便于快速对比实验。
- 包含6种评估指标，支持从稳定到持续变化环境的渐进式测试。
- 适合研究终身学习、可塑性机制或想快速验证新算法的研究者。
开发具备终身学习能力的智能体对通用人工智能（AGI）至关重要。然而，深度强化学习系统常面临可塑性丧失问题，即神经网络在训练过程中逐渐失去适应能力。尽管该问题意义重大，但领域内缺乏统一的基准和评估协议。我们提出Plasticine，首个用于深度强化学习可塑性优化的开源基准框架。该框架提供超过13种缓解方法的单文件实现，包含6种评估指标，并设计了从标准环境到持续变化环境的递增非平稳性学习场景。该框架使研究人员能够系统量化可塑性损失、评估缓解策略，并分析不同情境下的可塑性动态。相关文档、示例及源码已公开于https://github.com/RLE-Foundation/Plasticine。
原文摘要 · Abstract (English)
Developing lifelong learning agents is crucial for artificial general intelligence (AGI). However, deep reinforcement learning (RL) systems often suffer from plasticity loss, where neural networks gradually lose their ability to adapt during training. Despite its significance, this field lacks unified benchmarks and evaluation protocols. We introduce Plasticine, the first open-source framework for benchmarking plasticity optimization in deep RL. Plasticine provides single-file implementations of over 13 mitigation methods, 6 evaluation metrics, and learning scenarios with increasing non-stationarity levels from standard to continually varying environments. This framework enables researchers to systematically quantify plasticity loss, evaluate mitigation strategies, and analyze plasticity dynamics across different contexts. Our documentation, examples, and source code are available at https://github.com/RLE-Foundation/Plasticine.
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。