Organized Session

[2Q1-OS-27a] 強化学習の新展開

Wed. Jun 7, 2023 9:00 AM - 10:40 AM Room Q (601)

オーガナイザ：太田宏之、甲野佑、高橋達二

+Add all to schedule

9:00 AM - 9:20 AM

[2Q1-OS-27a-01] Theory of internal reinforcement learning

Introduction of quality into values

〇Tatsuji Takahashi Takahashi^1,2 (1. Tokyo Denki University, 2. RIKEN Center for Advanced Intelligence Project (AIP))

9:20 AM - 9:40 AM

[2Q1-OS-27a-02] Offline Model-Based Imitation Learning with Entropy Regularization of Model and Policy

〇Eiji Uchibe¹ (1. Advanced Telecommunications Research Institute International)

9:40 AM - 10:00 AM

[2Q1-OS-27a-03] Non-Markovian environment and experience replay

〇Hiroyuki Ohta¹, Kohki Higuchi², Takahashi Tatsuji², Ishizuka Toshiaki¹ (1. National Defense Medical College, 2. Tokyo Denki University)

10:00 AM - 10:40 AM

[2Q1-OS-27a-04] (OS invited talk) On Various Problem Settings of Sequential Decision Making and How Prior Knowledge of Problems Affects Theoretical Guarantees

〇Tadashi Kozuno¹, Toshinori Kitamura², Yuki Ichihara^3,4, Makoto Hagiwara⁵ (1. OMRON SINIC X Corporation, 2. University of Tokyo, 3. Nara Institute of Science and Technology, 4. Advanced Telecommunications Research Institute International, 5. pluszero)

Organized Session

[2Q4-OS-27b] 強化学習の新展開

Wed. Jun 7, 2023 1:30 PM - 3:10 PM Room Q (601)

オーガナイザ：太田宏之、甲野佑、高橋達二

+Add all to schedule

1:30 PM - 1:50 PM

[2Q4-OS-27b-01] A unified control mechanism for action planning, execution, dialogue, and inference for the reward maximization

〇Yuuji Ichisugi¹, Hidemoto Nakada¹, Naoto Takahashi¹, Izumi Takeuti¹, Takashi Sano² (1. AIST, 2. Toyo University)

[[Online]]

1:50 PM - 2:10 PM

[2Q4-OS-27b-02] Target-oriented Exploration in Deep Reinforcement Learning

〇Yu Kono^1,2, Jun Kume¹, Ikeda Ryuji³, Tatsuji Takahashi¹ (1. Tokyo Denki University, School of Science and Engineering, 2. DeNA Co., Ltd., 3. Graduate School of Tokyo Denki University)

2:10 PM - 2:30 PM

[2Q4-OS-27b-03] Emulation in reinforcement learning

〇Reina Kitade¹, Takuma Wada², Yu Kono¹, Tatsuji Takahashi¹ (1. Tokyo Denki University, 2. Graduate School of Tokyo Denki University)

2:30 PM - 2:50 PM

[2Q4-OS-27b-04] Expansion to Gaussian Distributional Rewards in Natural Reinforcement Learning

〇Shoma Ogawa¹, Shuichi Arimura², Tatsuji Takahashi¹, Yu Kohno¹ (1. School of Science and Engineering, Tokyo Denki University, 2. Graduate School of Tokyo Denki University)

2:50 PM - 3:10 PM

[2Q4-OS-27b-05] Top-level battle AI of The Modern Mobile Game "Gyakuten Othellonia" by Using Reinforcement Learning

〇Katsuki Ohto Ohto¹, Yuta Goto², Yu Kono¹, Ikki Tanaka¹ (1. DeNA Co., Ltd., 2. Tokyo University of Agriculture and Technology)

Sessions

Organized Session » OS-27