behavior-cloning

Dobb·E: An open-source, general framework for learning household robotic manipulation

RL based agent for browser-based multiplayer battle royale game «surviv.io»

This repository contains the code for the CVPR 2020 paper "Exploring Data Aggregation in Policy Learning for Vision-based Urban Autonomous Driving"

stable-baselines with JAX & Haiku

Machine learning robotics engineer preparation material.

Use traditional and convolutional neural networks to the clone driving behavior and then drive a race car in a simulator

Self-driving Car Nano-degree. Behavior cloning. Driving simulation.

Visual behavior cloning policy for skill-chaining.

Implemented Behavior Cloning, DAgger, Double Q-Learning, Dueling DQN, and Proximal Policy Optimization (PPO) in a simulated environment and analyzed/compared their performance in terms of efficiency, stability, and generalization.