Learning to Reason in Reinforcement Learning

在强化学习中学习推理

• 批准号: DP240103278
• 负责人: Dr Ehsan Abbasnejad
• 金额: $ 37.67万
• 依托单位: The University of Adelaide
• 依托单位国家: 澳大利亚
• 项目类别: Discovery Projects
• 财政年份: 2024
• 资助国家: 澳大利亚
• 起止时间: 2024-01-01 至 2026-12-31
• 项目状态: 未结题
• 来源: https://dataportal.arc.gov.au/RGS/Web/Grants/DP240103278
• 关键词: Learning; Reason; Reinforcement

Deep Reinforcement Learning (RL) uses deep neural networks to represent and learn optimal decision-making policies for intelligent agents in complex environments. However, most RL approaches require millions of episodes to converge to good policies, making it difficult for RL to be applied in real-world scenarios taking significant resources. This project aims to equip RL with capabilities such as counterfactual reasoning and outcome anticipation to significantly reduce the number of interactions required, improve generalisation, and provide the agent with the capability to consider the cause-effects. These improvements would narrow the gap between AI and human capabilities and broaden the adoption of RL in real-world applications.

深度强化学习（RL）使用深度神经网络来表示和学习复杂环境中智能代理的最佳决策策略。然而，大多数强化学习方法需要数百万次训练才能收敛到良好的策略，这使得强化学习很难应用于占用大量资源的现实场景。该项目旨在为强化学习配备反事实推理和结果预期等能力，以显着减少所需的交互数量，提高泛化能力，并为智能体提供考虑因果关系的能力。这些改进将缩小人工智能和人类能力之间的差距，并扩大强化学习在现实世界应用中的采用。