Cartpole, LunarLander, BiPedal Walker

Created by team Voyager on July 23, 2022

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

GovGiggler - A Smart Government Assistant

GovGiggler is an AI-powered assistant transforming interactions with government services. It simplifies processes with smart document assistance, secure authentication, dynamic updates, and humorous chat support—making bureaucracy effort.

Hacktivate

Grok

AI-Driven Autonomous Web Interaction for Citizens

We propose a Gen AI-powered platform using Grok models to simplify navigation and automate tasks on government websites. This empowers citizens to access services independently, reducing reliance on personnel and enhancing accessibility.

NavigatorX

GroqGrok

citizen-connect

The Government Efficiency Analyzer evaluates and optimizes the performance of government projects, ensuring efficient resource allocation, timely delivery, and measurable outcomes to enhance public services.

tml

Generative Agents

Healytastic One Nation One Data Platform

Healytastic is an AI-powered platform that validates and manages government data efficiently. Using Grok, Python, Streamlit, and Firebase (demo tech stack), it automates anomaly detection, deduplication, compliance checks for government systems.

Ueberanalyse

GrokstreamlitAI/ML API