activity
20242026
collaborators

13 papers

cs.RO2026

Learning Physical Interaction: A Survey of Tactile- and Force-aware Robot Learning

Shilin Shan, Chuhao Zhou, Ruize Wang +30

Physically grounded robot intelligence requires robots to perceive, reason about, and regulate their interactions with the physical world. This capability is particularly critical…

cs.LG2026

Learning the Supports for Categorical Critic in Reinforcement Learning

Jen-Yen Chang, Takayuki Osa, Tatsuya Harada

Value functions are an essential component in actor-critic based deep reinforcement learning (RL). Conventionally, these functions are trained as a regression task by minimising th…

cs.AI2026

Self-Supervised Theorem Discovery in a Formal Axiomatic System

Kazuki Ota, Takayuki Osa, Tatsuya Harada

Recent artificial intelligence (AI) systems have shown remarkable progress in mathematical reasoning. Many existing approaches, including large language models (LLMs), draw on huma…

cs.LG2026

Revisiting Regularized Policy Optimization for Stable and Efficient Reinforcement Learning in Two-Player Games

Kazuki Ota, Takayuki Osa, Motoki Omura +1

Two-player games such as board games have long been used as traditional benchmarks for reinforcement learning. This work revisits a policy optimization method with reverse Kullback…

cs.RO2026

World Model for Robot Learning: A Comprehensive Survey

Bohan Hou, Gen Li, Jindou Jia +15

World models, which are predictive representations of how environments evolve under actions, have become a central component of robot learning. They support policy learning, planni…

cs.LG2026

R2-Dreamer: Redundancy-Reduced World Models without Decoders or Augmentation

Naoki Morihira, Amal Nahar, Kartik Bharadwaj +3

A central challenge in image-based Model-Based Reinforcement Learning (MBRL) is to learn representations that distill essential information from irrelevant visual details. While pr…