Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Self-Supervised Representation Learning as Multimodal Variational Inference


Mar 22, 2022
Hiroki Nakamura, Masashi Okada, Tadahiro Taniguchi

* 4 pages, 4 figures, work in progress 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Multi-View Dreaming: Multi-View World Model with Contrastive Learning


Mar 15, 2022
Akira Kinose, Masashi Okada, Ryo Okumura, Tadahiro Taniguchi

* 7 pages, 8 figures 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

DreamingV2: Reinforcement Learning with Discrete World Models without Reconstruction


Mar 01, 2022
Masashi Okada, Tadahiro Taniguchi

* The code will be available soon 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Dreaming: Model-based Reinforcement Learning by Latent Imagination without Reconstruction


Jul 29, 2020
Masashi Okada, Tadahiro Taniguchi


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

PlaNet of the Bayesians: Reconsidering and Improving Deep Planning Network by Incorporating Bayesian Inference


Mar 01, 2020
Masashi Okada, Norio Kosaka, Tadahiro Taniguchi


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Domain-Adversarial and -Conditional State Space Model for Imitation Learning


Jan 31, 2020
Ryo Okumura, Masashi Okada, Tadahiro Taniguchi

* 7 pages, 5 figures 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Multi-person Pose Tracking using Sequential Monte Carlo with Probabilistic Neural Pose Predictor


Sep 16, 2019
Masashi Okada, Shinji Takenaka, Tadahiro Taniguchi


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Variational Inference MPC for Bayesian Model-based Reinforcement Learning


Jul 08, 2019
Masashi Okada, Tadahiro Taniguchi


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Path Integral Networks: End-to-End Differentiable Optimal Control


Jun 29, 2017
Masashi Okada, Luca Rigazio, Takenobu Aoshima


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email