lablab.ai logo - Community innovating and building with artificial intelligence
Cartpole, LunarLander, BiPedal Walker

Cartpole, LunarLander, BiPedal Walker

Created by team Voyager on July 23, 2022
OpenAI gymReinforcement Learning

Applied reinforcement learning for agent to play these 3 games: Cartpole, LunarLander, BiPedal Walker. We used the basic model of Environment -> State -> Agent -> Action to train our agent. We reward the agent for achieving an outcome that we want, while penalizing the agent for doing otherwise. After many iterations, our agents learns to clear the games.

Category tags:
Presentation
Explore more applications

Unleashing Creativity with Yi 34B and Langchain

Revolutionizing Research: Unleashing Creativity with Yi 34B and Langchain

arxiv researcher and Yi34B

Yi-LLMSLangChain

Mura AI

Mura AI is an empathetic health assistant platform leveraging advanced AI to provide informative guidance on wellness, nutrition, and mental health support.

Road to AGI

Yi-LLMS

Artificial General Yintelligence

AGYIntelligence revolutionizes enterprise solutions by creating multi-agent environments where each AI agent possesses an unlimited context window, ensuring unparalleled depth and breadth in data analysis and decision-making.

Yi Tonic 200k

Yi-LLMSCustom GPTs

SahaAI

A digital platform aimed at supporting mental health through artificial intelligence.

SahaAI

Yi-LLMS

Talk to DB

Talk to DB is a handy chatbot style helper that presents the user with helpful data about whatever dataset is loaded or connected. The user can ask relevant questions about the data that is present in the dataset.

AI innovators

Yi-LLMS