Size independent neural transfer for rddl planning

S Garg, A Bajpai - Proceedings of the International Conference on …, 2019 - aaai.org
Neural planners for RDDL MDPs produce deep reactive policies in an offline fashion. These
scale well with large domains, but are sample inefficient and time-consuming to train from …
被引用次数：48 相关文章

Size Independent Neural Transfer for RDDL Planning

S Garg, A Bajpai - arXiv preprint arXiv:1902.03081, 2019 - arxiv.org
Neural planners for RDDL MDPs produce deep reactive policies in an offline fashion. These
scale well with large domains, but are sample inefficient and time-consuming to train from …

Size Independent Neural Transfer for RDDL Planning

S Garg, A Bajpai - arXiv e-prints, 2019 - ui.adsabs.harvard.edu
Neural planners for RDDL MDPs produce deep reactive policies in an offline fashion. These
scale well with large domains, but are sample inefficient and time-consuming to train from …

Size Independent Neural Transfer for RDDL Planning

S Garg, A Bajpai - Proceedings of the International Conference on …, 2019 - ojs.aaai.org
Neural planners for RDDL MDPs produce deep reactive policies in an offline fashion. These
scale well with large domains, but are sample inefficient and time-consuming to train from …