deepmind-lab 开源项目推荐（22 个）

algorithmicsuperintelligence /openevolve

AlphaEvolve 的开源实现

Farama-Foundation /Shimmy

PettingZoo and Gymnasium bindings for popular reinforcement learning environments outside of Farama

google-research /seed_rl

SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference. Implements IMPALA and R2D2 algorithms in TF2 with SEED's architecture.

miyosuda /unreal

Reinforcement learning with unsupervised auxiliary tasks

tgangwani /GA3C-DeepNavigation

Tensorflow implementation of DeepMind paper - "Learning to Navigate in Complex Environments"

mtrazzi /meta_rl

The Tensorflow code and a DeepMind Lab wrapper for my article "Meta-Reinforcement Learning" on FloydHub.

ducandu /RL-Implementation-IMPALA

A Test-Implementation of the IMPALA algorithm (by deepmind 2018)

CEC-Agent /CEC

Official Implementation of NeurIPS'23 Paper "Cross-Episodic Curriculum for Transformer Agents"

hari7261 /AI-Tutor

A privacy-focused tutoring assistant that explains concepts step-by-step and generates quizzes (MCQs). Works 100% offline with Ollama (Gemma/Llama3).

avdmitry /rl_3d

Reinforcement learning in 3D.

IDSIA /rtrl-elstm

Official repository for the paper "Exploring the Promise and Limits of Real-Time Recurrent Learning" (ICLR 2024)

BKHMSI /Meta-RL-Harlow

PyTorch implementation of two variants of the Harlow visual fixation task (PsychLab and 1D version). Reproduces the results found in two papers. Check the ReadMe for more details!

ddayzzz /deepmind_lab_gym_wrapper

Deepmind lab gym-like wrapper

MitchellTesla /lab

A customizable 3D platform for agent-based AI research

yunfanjiang /drl-rws

CS 238 Final Project: Deep Reinforcement Learning Agents that Run with Scissors

IngyN /rl

Using deepmind lab for RL

xueeinstein /rl-docker-hub

Docker hub for easily setting up reinforcement learning research environment

333Technologies /QASM256

QASM256: A groundbreaking quantum-classical hybrid programming language designed for AI, secure systems, and real-time optimization, pushing the boundaries of innovation across industries.

hari7261 /Document-Q-A-LLM

A document question-answering system that allows users to upload files (PDFs, DOCs, TXTs) and ask questions about their content using RAG (Retrieval-Augmented Generation) with ChromaDB and Gemma.

DamienLegros /harlow

Projet IAR master 2 ANDROIDE : 2021 - 2022 Projet d'introduction au méta reinforcement learning codé en Python