-
Exploration Metrics for Reinforcement Learning
The dataset used in the paper is a set of data generated from four different types of distributions: uniform, truncated normal, bi-modal truncated normal growing scale, and... -
Navigating Assistance System for Quadcopter with Deep Reinforcement Learning
A deep reinforcement learning method for quadcopter to bypass obstacles in 3D environment. -
Reward hacking
The dataset consists of four RL environments with misspecified rewards, including traffic control, COVID response, blood glucose monitoring, and the Atari game Riverraid. -
MountainCar environment
The authors used the MountainCar environment for reinforcement learning experiments. -
Autonomous Reinforcement Learning of Multiple Interrelated Tasks
The dataset used in the paper is a simulated robotic scenario involving multiple interrelated tasks. -
Scripted pick and place policy
Scripted pick and place policy -
Scripted grasping policy
Scripted grasping policy -
Task-specific data
Task-specific data -
Prior dataTask data
Prior dataTask data -
Linear Quadratic Regulator (LQR)
The Linear Quadratic Regulator (LQR) dataset is used to study the sample complexity of model-based and model-free algorithms for policy evaluation and policy optimization. -
Gridworld Environments and Sokoban Puzzles
The dataset used in the paper is a set of gridworld environments and Sokoban puzzles. -
Multi-UAV Speed Control with Collision Avoidance and Handover-aware Cell Asso...
The dataset is used for multi-UAV speed control with collision avoidance and handover-aware cell association. The dataset is used to optimize the autonomous motion of multiple... -
Object Collection Game
The object collection game is a simple 2D video game that requires the agent to collect objects that move from the top of the screen to the bottom. -
ProcGen environments
The dataset used in the paper is a procedurally-generated (PCG) environment, specifically the MiniGrid and ProcGen environments. -
MiniGrid and ProcGen environments
The dataset used in the paper is a procedurally-generated (PCG) environment, specifically the MiniGrid and ProcGen environments. -
Fab-in-the-loop reinforcement learning for photonic component design
The fab-in-the-loop reinforcement learning algorithm for the design of nano-photonic components that accounts for the imperfections present in nanofabrication processes. -
Cassie Dataset
The dataset used in this paper is a closed-loop system of a bipedal robot Cassie controlled by a model-free reinforcement learning (RL) policy. -
Multi-goal Reach Task Dataset
The dataset used in the paper is a multi-goal reach task dataset, where the robot arm needs to reach a target pose with varying precision requirements. -
Optical Pulse Stacking
The OPS environment is an open-source simulator for controlling pulse stacking systems using RL algorithms. -
Discovering User Types: Mapping User Traits by Task-Specific Behaviors in Rei...
The dataset used in this paper is a set of behavior maps for various environments, including mHealth applications.
