Name: Jiayu Chen
Type: User
Company: Carnegie Mellon University
Bio: PostDoc at CMU CS, Ph.D. in IEOR from Purdue, mainly focus on Reinforcement Learning Algorithm Design and Applications
Location: Pittsburg, Pennsylvania
Blog: https://lucascjysdl.github.io/
Jiayu Chen's Projects
Tutorials on commonly-used basic AI techniques.
Justified MATLAB implementations of common numeric optimization algorithms for nonlinear and convex optmization.
An option discovery algorithm based on spectral clustering which can be used for continuous control tasks.
A Poker AI for Bridge based on self-playing with SOTA MARL algorithms and heuristic search.
An intelligent freight delivery scheduling system built with the SOTA MARL algorithms and an optimization solver.
This repository provides a survey on the applications of deep generative models for offline reinforcement learning and imitation learning. We cover multiple deep generative models, including VAEs, GANs, Normalizing Flows, Transformers, and Diffusion Models.
Applying SOTA imitation learning and meta-learning algorithms, such as GAIL, AIRL, Info-AIRL, Meta-AIRL, etc, for driving bahavior learning of autonomous vehicles.
A skill-based Poker AI -- Official implementation of "Hierarchical Deep Counterfactual Regret Minimization"
A novel Hierarchical Imitation Learning algorithm based on AIRL.
Applying Imitation Learning and Reinforcement Learning in Pedestrain Interaction for Autonomous Vehicles && Simulated with CARLA
Codes for the paper "Multi-task Hierarchical Adversarial Inverse Reinforcement Learning"
A novel Unsupervised Option Discovery algorithm based on Determinant Point Process.
Official implementation of the paper "Global Convergence Guarantees for Federated Policy Gradient Methods with Adversaries"
An option discovery algorithm for multi-agent reinforcement learning, including the tabular version and scalable NN-based version.
A Python implementation of the two-phase simplex method as an LP solver.