RLeXplore provides stable baselines of exploration methods in reinforcement learning, such as intrinsic curiosity module (ICM), random network distillation (RND) and rewarding impact-driven exploration (RIDE).

A platform for executing RRT exploration in ROS Noetic and Ubuntu 20.04LTS

A platform for executing RRT exploration in ROS Melodic and Ubuntu 18.04LTS

PyTorch implementation of Never Give Up: Learning Directed Exploration Strategies

Attention-based Curiosity-driven Exploration in Deep Reinforcement Learning

Motion planning and environment exploration with Bitcraze Crazyflie drones.

Repository for coExplore: Combining multiple rankings for multi-robot exploration

An open source reinforcement learning codebase with a variety of intrinsic exploration methods implemented in PyTorch.

Deep Recurrent Q-Network with different exploration strategies for self-driving cars (using AirSim)

An adaptive trajectory-constrained exploration strategy

Autonomous Turtlebot3 Waffle PI capable of autonomous SLAM using Nav2 and Cartographer

Image processing using sequenced programming and turtle functions.

code for reproducing results in paper on skill based exploration

Implementation of Reinforcement Learning in Fall 2018

Trying to apply Deep RL + Geometric DL to graphs exploration

Reference implementation of the Parameterized Indexed Networks

Exploration methods in Deep Reinforcement Learning.

rrt/bfs/path_transform exploration algo for autonomous vehicle.

Code for the paper "Randomized Exploration in Cooperative Multi-Agent Reinforcement Learning", Advances in Neural Information Processing Systems (NeurIPS) 2024

A reinforcement learning agent trained using Q-Learning to solve OpenAI Gym’s FrozenLake environment. The project demonstrates value-based learning, policy improvement, and exploration strategies in a slippery gridworld setting.