Yuu David Jinnai's repositories
Best-Papers
Best Papers nominees from top conferences related to Artificial Intelligence
Optimal-Options-ICML-2019
Code for generating options for planning and reinforcement learning
Parallel-Best-First-Searches
The source code for the HDA*, PBNF algorithm, and friends.
distributed-fast-downward
Distributed Fast Downward: classical planner for parallel/distributed environments
Atari-iterative-width
Dominated Action Sequence Detection for Online Blind Planning applied in Arcade Learning Environment (Atari)
Hash-Distributed-Astar
Hash Distributed A*
combinatorial_instances
Instance generators for combinatorial search domains: 15-puzzle, 24-puzzle, grid-pathfinding, multiple sequenece alignment
covering-options
covering-options
tensorforce
TensorForce: A TensorFlow library for applied reinforcement learning
Asymmetric-k-center
Implementation of an O(log* k) approximation algorithm (Archer 2001) for asymmetric k-center problem.
BPIDA-appendix
supplemental material for SoSC 2017 paper https://aaai.org/ocs/index.php/SOCS/SOCS17/paper/view/15801
ContinuousSPM
Significant pattern mining for continuous variables (reimplementation of Sugiyama&Borgwardt https://arxiv.org/abs/1702.08694)
icml2016-minecraft
Implementation of "Control of Memory, Active Perception, and Action in Minecraft"
LLM-Blender
[ACL2023] We introduce LLM-Blender, an innovative ensembling framework to attain consistently superior performance by leveraging the diverse strengths of multiple open-source LLMs. LLM-Blender cut the weaknesses through ranking and integrate the strengths through fusing generation to enhance the capability of LLMs.
open-llm-leaderboard-local
Open LLM Leaderboard のローカル実行用スクリプト
temperature-monitor
Temperature monitor for cluster. It pretty much depends on each hardware so that just pulling this code won't work.
TensorFlow-Examples
TensorFlow Tutorial and Examples for Beginners with Latest APIs
trl
Train transformer language models with reinforcement learning.