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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Dropout Q-Functions for Doubly Efficient Reinforcement Learning


Oct 05, 2021
Takuya Hiraoka, Takahisa Imagawa, Taisei Hashimoto, Takashi Onishi, Yoshimasa Tsuruoka

* Source code: https://github.com/TakuyaHiraoka/Dropout-Q-Functions-for-Doubly-Efficient-Reinforcement-Learning 

   Access Paper or Ask Questions

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

Off-Policy Meta-Reinforcement Learning Based on Feature Embedding Spaces


Jan 06, 2021
Takahisa Imagawa, Takuya Hiraoka, Yoshimasa Tsuruoka

* 14pages 

   Access Paper or Ask Questions

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

Meta-Model-Based Meta-Policy Optimization


Jun 05, 2020
Takuya Hiraoka, Takahisa Imagawa, Voot Tangkaratt, Takayuki Osa, Takashi Onishi, Yoshimasa Tsuruoka


   Access Paper or Ask Questions

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

Optimistic Proximal Policy Optimization


Jun 25, 2019
Takahisa Imagawa, Takuya Hiraoka, Yoshimasa Tsuruoka

* Exploration in RL (workshop @ ICML2019) 

   Access Paper or Ask Questions

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

Learning Robust Options by Conditional Value at Risk Optimization


Jun 11, 2019
Takuya Hiraoka, Takahisa Imagawa, Tatsuya Mori, Takashi Onishi, Yoshimasa Tsuruoka

* Video demo: https://drive.google.com/open?id=1xXgSeEa_nNG397ZkIayk3CwYPy_BPy8X 

   Access Paper or Ask Questions

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

Optimization of Information-Seeking Dialogue Strategy for Argumentation-Based Dialogue System


Nov 26, 2018
Hisao Katsumi, Takuya Hiraoka, Koichiro Yoshino, Kazeto Yamamoto, Shota Motoura, Kunihiko Sadamasa, Satoshi Nakamura

* Accepted by AAAI2019 DEEP-DIAL 2019 workshop 

   Access Paper or Ask Questions

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

Refining Manually-Designed Symbol Grounding and High-Level Planning by Policy Gradients


Sep 29, 2018
Takuya Hiraoka, Takashi Onishi, Takahisa Imagawa, Yoshimasa Tsuruoka

* presented at the IJCAI-ICAI 2018 workshop on Learning & Reasoning (L&R 2018) 

   Access Paper or Ask Questions

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

Monte Carlo Tree Search with Scalable Simulation Periods for Continuously Running Tasks


Sep 07, 2018
Seydou Ba, Takuya Hiraoka, Takashi Onishi, Toru Nakata, Yoshimasa Tsuruoka


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
>>