Steady state analysis of episodic reinforcement learning

H Bojun - Advances in Neural Information Processing …, 2020 - proceedings.neurips.cc
Reinforcement Learning (RL) tasks generally divide into two kinds: continual learning and
episodic learning. The concept of steady state has played a foundational role in the …
被引用次数：21 相关文章

Steady State Analysis of Episodic Reinforcement Learning

H Bojun - Advances in Neural Information Processing …, 2020 - proceedings.neurips.cc
Reinforcement Learning (RL) tasks generally divide into two kinds: continual learning and
episodic learning. The concept of steady state has played a foundational role in the …

Steady state analysis of episodic reinforcement learning

H Bojun - Proceedings of the 34th International Conference on …, 2020 - dl.acm.org
This paper proves that the episodic learning environment of every finite-horizon decision
task has a unique steady state under any behavior policy, and that the marginal distribution …

Steady State Analysis of Episodic Reinforcement Learning

H Bojun - arXiv e-prints, 2020 - ui.adsabs.harvard.edu
This paper proves that the episodic learning environment of every finite-horizon decision
task has a unique steady state under any behavior policy, and that the marginal distribution …

Steady State Analysis of Episodic Reinforcement Learning

H Bojun - arXiv preprint arXiv:2011.06631, 2020 - arxiv.org
This paper proves that the episodic learning environment of every finite-horizon decision
task has a unique steady state under any behavior policy, and that the marginal distribution …