matsuolab's repositories
roomba_hack
ロボットシステム入門 / Let's learn how to create intelligent robot systems with Roomba!
hsr-clip-fields
clip fields for HSR
roomba_hack_course
ロボットシステム入門テキスト / Let's learn how to create intelligent robot systems with Roomba! Source code: https://github.com/matsuolab/roomba_hack
Variance-Weighted-MDVI
Official Implementations of "Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice"
llm-leaderboard
Project of llm evaluation to Japanese tasks
Uniform-PAC-Primal-Dual-CMDP
Official implementations of "A Policy Gradient Primal-Dual Algorithm for Constrained MDPs with Uniform PAC Guarantees"
Deep-Variance-Weighting-MinAtar
Official Implementations of "Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice"
Megatron-DeepSpeed
Ongoing research training transformer language models at scale, including: BERT & GPT-2
realsense_docker
Docker Image and launchfile for realsense devices. Modified from https://github.com/amslabtech/realsense_docker
rosbag_dataset
ROS package for making datasets with rosbag
wisteria_simple
A Simple Tutorial on Wisteria
crane_x7_description
ROS / ROS 2 package with URDF description macro for CRANE-X7
crane_x7_ros
CRANE-X7 ROS / ROS 2 Packages.
Deep-Variance-Weighting-Maze
Official Implementation of "Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice"
FastChat
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
llm-leaderboard-v1
Project of llm evaluation to Japanese tasks
nejumi-leaderboard
Project of llm evaluation to Japanese tasks
RCMDP-Epigraph
Official Implementations of "Near-Optimal Policy Identification in Robust Constrained Markov Decision Processes via Epigraph Form" [Experiments in Section 7]
rlds_dataset_builder
An example RLDS dataset builder for X-embodiment dataset conversion.
robomimic
robomimic: A Modular Framework for Robot Learning from Demonstration
robot_navigation
Autonomous navigation for general purpose service robots