arXiv:2305.18388
The Statistical Benefits of Quantile Temporal-Difference Learning for Value Estimation
원문 초록
We study the problem of temporal-difference-based policy evaluation in reinforcement learning. In particular, we analyse the use of a distributional reinforcement learning algorithm, quantile temporal-difference learning (QTD), for this task. We reach the surprising conclusion that even if a practitioner has no interest in the return distribution beyond the mean, QTD (which learns predictions about the full distribution of returns) may offer performance superior to approaches such as classical TD learning, which predict only the mean return, even in the tabular setting.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Distributional Reinforcement Learning on Path-dependent Options
CTRLS: Chain-of-Thought Reasoning via Latent State-Transition
Refining Few-Step Text-to-Multiview Diffusion via Reinforcement Learning
Fully Offline Reinforcement Learning
High-Throughput Distributed Reinforcement Learning via Adaptive Policy Synchronization
Step-wise Policy for Rare-tool Knowledge (SPaRK): Offline RL that Drives Diverse Tool Use in LLMs
토론
이 논문과 연결된 포럼 글이 아직 없습니다.