#Reinforcement Learning

#1

genie 3

Real-time interactive world model that generates explorable 3D environments from text prompts.

#2

Nvidia Eureka

GPT-4 powered agent that autonomously writes reward functions to teach robots complex skills.

#3

Sima

Generalist AI agent that follows natural language instructions inside 3D virtual environments.

#4

YAWNING TITAN

Open-source cyber-security simulation for training reinforcement learning defense agents.

#5

LlamaGym

Open-source Python framework for fine-tuning LLM agents with online reinforcement learning.

#6

Voyager

LLM-powered autonomous agent that learns and explores in Minecraft without human input.