1 citations · 1 across the 6 of their papers we have counts for
6 papers
Strongly Solving 2048 4x3
Tomoyuki Kaneko, Shuhei Yamashita
2048 is a stochastic single-player game involving 16 cells on a 4 by 4 grid, where a player chooses a direction among up, down, left, and right to obtain a score by merging two til…
The Role of Background Information in Reducing Object Hallucination in Vision-Language Models: Insights from Cutoff API Prompting
Masayo Tomita, Katsuhiko Hayashi, Tomoyuki Kaneko
Vision-Language Models (VLMs) occasionally generate outputs that contradict input images, constraining their reliability in real-world applications. While visual prompting is repor…
DEIR: Efficient and Robust Exploration through Discriminative-Model-Based Episodic Intrinsic Rewards
Shanchuan Wan, Yujin Tang, Yingtao Tian +1
Exploration is a fundamental aspect of reinforcement learning (RL), and its effectiveness is a deciding factor in the performance of RL algorithms, especially when facing sparse ex…
Learning Diverse Options via InfoMax Termination Critic
Yuji Kanagawa, Tomoyuki Kaneko
We consider the problem of autonomously learning reusable temporally extended actions, or options, in reinforcement learning. While options can speed up transfer learning by servin…
Playing Catan with Cross-dimensional Neural Network
Quentin Gendre, Tomoyuki Kaneko
Catan is a strategic board game having interesting properties, including multi-player, imperfect information, stochastic, complex state space structure (hexagonal board where each…
Rogue-Gym: A New Challenge for Generalization in Reinforcement Learning
Yuji Kanagawa, Tomoyuki Kaneko
In this paper, we propose Rogue-Gym, a simple and classic style roguelike game built for evaluating generalization in reinforcement learning (RL). Combined with the recent progress…