Papers of the day   All papers

CompILE: Compositional Imitation Learning and Execution

Comments

May 15 2019 Thomas Kipf

The camera-ready version of our CompILE @icmlconf paper is out! Differentiable sequence segmentation for option discovery in RL — w/ @liyuajia @egrefen @pushmeet @PeterWBattaglia et al. Paper: https://arxiv.org/abs/1812.01483 Code: https://github.com/tkipf/compile https://t.co/4RnGTGlEhr
0 replies, 159 likes


Dec 06 2018 Thomas Kipf

CompILE discovers composable segments & encodings of behavior from sequential data (unsupervised and differentiable). Codes can be recomposed to facilitate generalization and exploration in RL. New work with collaborators from @DeepMindAI Paper: https://arxiv.org/abs/1812.01483 https://t.co/K3V9mrMDb6
2 replies, 152 likes


Apr 22 2019 Thomas Kipf

An extended version of our CompILE paper was accepted to @icmlconf! See below for our earlier NeurIPS workshop version of the paper. https://twitter.com/thomaskipf/status/1070702916393156610
1 replies, 145 likes


Jun 11 2019 Thomas Kipf ✈️ ICML

Interested in discovering latent hierarchical structure and option discovery in RL? Come visit our talk/poster on CompILE at @icmlconf tomorrow! w/ @liyuajia @egrefen @pushmeet @PeterWBattaglia et al. Talk: Wed. 4:40-5:00pm, Hall B (Poster #56) Paper: https://arxiv.org/abs/1812.01483 https://t.co/pz4pjtIC8W
0 replies, 97 likes


Nov 07 2019 MONTREAL.AI

CompILE: Compositional Imitation Learning and Execution Kipf et al.: https://arxiv.org/abs/1812.01483 Code: https://github.com/tkipf/compile #ArtificialIntelligence #ImitationLearning #MachineLearning https://t.co/rFaBqx7FFB
0 replies, 2 likes


Content