arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2204.01464cs.LGcs.AI
收藏

值梯度加权基于模型的强化学习

Value Gradient weighted Model-Based Reinforcement Learning

Vector Institute(向量研究所);University of Toronto(多伦多大学);University of Waterloo(滑铁卢大学);Nvidia(英伟达)

Claas Voelcker, Victor Liao, Animesh Garg, Amir-massoud Farahmand

AI总结:

针对基于模型的强化学习中模型误差与策略目标不匹配问题,提出值梯度加权模型学习(VaGraM),在挑战性设置下提升性能,并在Mujoco基准上实现高回报且更稳健。

摘要:

基于模型的强化学习(MBRL)是一种获取控制策略的样本高效技术,但不可避免的建模误差常常导致性能下降。MBRL中的模型通常仅用于重建动态,特别是状态观测,而模型误差对策略的影响并未被训练目标所捕获。这导致了MBRL的预期目标(实现良好的策略和价值学习)与实际使用的损失函数目标(未来状态预测)之间的不匹配。直觉上,价值感知的模型学习能解决这一问题,事实上,基于理论分析已提出了几种针对此目标不匹配问题的解决方案。然而,在实践中它们往往不如常用的基于最大似然估计(MLE)的方法。本文提出了值梯度加权模型学习(VaGraM),一种新颖的价值感知模型学习方法,在具有挑战性的设置(如小模型容量和存在干扰状态维度)下提高了MBRL的性能。我们分析了MLE和价值感知方法,展示了它们在价值感知模型学习中未能考虑探索和函数逼近行为,并强调了在深度学习设置中稳定优化所需满足的额外目标。我们通过实验验证了我们的分析,表明我们的损失函数在Mujoco基准套件上能获得高回报,同时比基于最大似然估计的方法更稳健。

英文摘要:

Model-based reinforcement learning (MBRL) is a sample efficient technique to obtain control policies, yet unavoidable modeling errors often lead performance deterioration. The model in MBRL is often solely fitted to reconstruct dynamics, state observations in particular, while the impact of model error on the policy is not captured by the training objective. This leads to a mismatch between the intended goal of MBRL, enabling good policy and value learning, and the target of the loss function employed in practice, future state prediction. Naive intuition would suggest that value-aware model learning would fix this problem and, indeed, several solutions to this objective mismatch problem have been proposed based on theoretical analysis. However, they tend to be inferior in practice to commonly used maximum likelihood (MLE) based approaches. In this paper we propose the Value-gradient weighted Model Learning (VaGraM), a novel method for value-aware model learning which improves the performance of MBRL in challenging settings, such as small model capacity and the presence of distracting state dimensions. We analyze both MLE and value-aware approaches and demonstrate how they fail to account for exploration and the behavior of function approximation when learning value-aware models and highlight the additional goals that must be met to stabilize optimization in the deep learning setting. We verify our analysis by showing that our loss function is able to achieve high returns on the Mujoco benchmark suite while being more robust than maximum likelihood based approaches.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑