Name: Zhengyao Jiang
Type: User
Company: University College London
Bio: PhD student at UCL, Interested in Offline Reinforcement Learning (RL), Data-Efficient RL and Neuro-Symbolic Methods for RL.
Twitter: zhengyaojiang
Location: London, UK
Blog: zhengyaojiang.github.io
Zhengyao Jiang's Projects
Collection of LLM resources that can be used to build products you can "own" or to perform reproducible research.
Google Cardboard
A benchmark for offline reinforcement learning.
Official codebase for Decision Transformer: Reinforcement Learning via Sequence Modeling.
Mastering Atari with Discrete World Models
Framework of DataLog Neural Program Synthesis
Code release for Graph Backup: Data Efficient Backup Exploiting Markovian Transitions https://arxiv.org/abs/2205.15824
Source code of "Grid-to-Graph: Flexible Spatial Relational Inductive Biases for Reinforcement Learning" (AAMAS 2021).
Code release for Efficient Planning in a Compact Latent Action Space (ICLR2023) https://arxiv.org/abs/2208.10291.
The virtual reality controlled by mental command and voice
Neural style in TensorFlow! :art:
Source code of Neural Logic Reinforcement Learning (https://arxiv.org/abs/1904.10729)
End-to-End Differentiable Proving
Online Portfolio Selection toolbox
Convert PDF files into markdown files
PGPortfolio: Policy Gradient Portfolio, the source code of "A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem"(https://arxiv.org/pdf/1706.10059.pdf).
A high-performance distributed execution engine
Attempting to replicate "A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem" https://arxiv.org/abs/1706.10059 (and an openai gym environment)
build tensorflow high level rnn api from scratch
a programming game ,in which you can use code to control the tank.
Author's PyTorch implementation of TD3+BC, a simple variant of TD3 for offline RL
Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.
Computation using data flow graphs for scalable machine learning
Deep learning library featuring a higher-level API for TensorFlow.
UCL Deciding, Acting, and Reasoning with Knowledge (DARK) Lab
UCL LaTeX thesis templates.