-
IBM Research
- Yokrtown Heights, NY
- https://scholar.google.com/citations?user=kigtlXEAAAAJ&hl=en
- in/junkyul
Highlights
- Pro
Stars
[BIRD-INTERACT] Re-imagines Text-to-SQL evaluation via lens of dynamic interactions.
Prompt Declaration Language (PDL) is a declarative prompt programming language.
This repository is a supplementary material.
Planning annotated Reinforcement Learning (PaRL) Agent annotations
Planning annotated Reinforcement Learning (PaRL) Agents
Planning annotated Reinforcement Learning (PaRL) Agent minigrid enviroment
aider is AI pair programming in your terminal
Agentics is a Python framework that provides structured, scalable, and semantically grounded agentic computation.
Long-form factuality assessor for large language models
Learning representations for RL in Healthcare under a POMDP assumption
Open AI Gym Environment For MIMIC Dataset Sepsis Patient
K* search based implementation of top-k and top-quality planners
A curated list of practical guide resources of LLMs (LLMs Tree, Examples, Papers)
This is the official implementation of NeurIPS 2022 paper "Generalizing Goal-Conditioned Reinforcement Learning with Variational Causal Reasoning"
Official data and code for our paper Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning
Implementation codes and datasets used in ICLR'22 Spotlight paper AdaRL: What, Where, and How to Adapt in Transfer Reinforcement Learning.
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
Random syntax generator with reasoner and LSTM
Convert Machine Learning Code Between Frameworks
"Probabilistic Machine Learning" - a book series by Kevin Murphy
Code for "Planning from Pixels using Inverse Dynamics Models"
Code for "Learning to Reach Goals via Iterated Supervised Learning"