ltzheng

Cradle

The Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curation, in a standardized general environment with minimal requirements.

agent-studio

Environments, tools, and benchmarks for general computer agents

alphafold

Open source code for AlphaFold.

CurriculumMARL

Code of "Towards Skilled Population Curriculum for MARL" + Implementation of Curriculum MARL algorithms based on Ray

data-privacy

Preserve data privacy with k-anonymity (samarati & mondrian), differential privacy, federated learning, paillier homomorphic encryption, etc.

mappo-football

Multi-Agent PPO (MAPPO) with the Google Research Football environment.

parallel-computing-ustc

Experiments for the Parallel Computing course

pddpg-hfo

Half Field Offense in Robocup 2D Soccer with reinforcement learning

Replica-Currency-Estimation

Python implementation of Replica Currency Estimation

Synapse

[ICLR 2024] Trajectory-as-Exemplar Prompting with Memory for Computer Control

ltzheng/data-privacy

Preserve data privacy with k-anonymity (samarati & mondrian), differential privacy, federated learning, paillier homomorphic encryption, etc.

ltzheng/Synapse

[ICLR 2024] Trajectory-as-Exemplar Prompting with Memory for Computer Control

ltzheng/pddpg-hfo

Half Field Offense in Robocup 2D Soccer with reinforcement learning

ltzheng/CurriculumMARL

Code of "Towards Skilled Population Curriculum for MARL" + Implementation of Curriculum MARL algorithms based on Ray

ltzheng/mappo-football

Multi-Agent PPO (MAPPO) with the Google Research Football environment.

ltzheng/parallel-computing-ustc

Experiments for the Parallel Computing course

ltzheng/Replica-Currency-Estimation

Python implementation of Replica Currency Estimation

ltzheng/alphafold

Open source code for AlphaFold.

ltzheng/CDS

ltzheng/coinrun

Code for the paper "Quantifying Transfer in Reinforcement Learning"

ltzheng/football

Google football with more wrappers, scenarios and flexible task parameters

ltzheng/formal-methods-ustc

Experiments for the Formal Methods course

ltzheng/numerical-analysis

Assignments for the Numerical Methods course at USTC

ltzheng/OFDClean

Contextual Data Cleaning with Ontological Functional Dependencies

ltzheng/pymarl2

Rethinking the Importance of Implementation Tricks in Multi-Agent Reinforcement Learning

ltzheng/DexterousHands

This is a library that provides dual dexterous hand manipulation tasks through Isaac Gym

ltzheng/dm_control

DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.

ltzheng/dmc2gym

OpenAI Gym wrapper for the DeepMind Control Suite

ltzheng/EfficientZero

Open-source codebase for EfficientZero, from "Mastering Atari Games with Limited Data" at NeurIPS 2021.

ltzheng/jafar

JAX reimplementation of the DeepMind paper "Genie: Generative Interactive Environments"

ltzheng/ltzheng.github.io

ltzheng/muzero-general

MuZero

ltzheng/open_spiel

OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.

ltzheng/overcooked_ai

A benchmark environment for fully cooperative human-AI performance.

ltzheng/pix2act

ltzheng/ray

An open source framework that provides a simple, universal API for building distributed applications. Ray is packaged with RLlib, a scalable reinforcement learning library, and Tune, a scalable hyperparameter tuning library.

ltzheng/stanford_alpaca

Code and documentation to train Stanford's Alpaca models, and generate the data.

ltzheng/vllm

A high-throughput and memory-efficient inference and serving engine for LLMs