-
Road Runner
The dataset used in the paper is not explicitly described, but it is mentioned that the authors used a symbolic reinforcement learning algorithm to learn end-to-end control... -
Open Bandit Dataset and Pipeline
Open bandit dataset and pipeline: Towards realistic and reproducible off-policy evaluation -
REWARD (MIS)DESIGN FOR AUTONOMOUS DRIVING
The dataset used in the paper is a collection of reward functions for autonomous driving, which are designed to evaluate the performance of reinforcement learning agents. -
Uncertainty-Aware Model-Based Reinforcement Learning with Application to Auto...
The proposed uncertainty-aware model-based reinforcement learning framework is applied to end-to-end autonomous driving tasks. -
Hungry Geese
The Hungry Geese environment is a discrete environment where four geese are placed on a 7x11 grid, and the goal is to collect food while avoiding collisions with other geese. -
Modularity in Reinforcement Learning via Algorithmic Independence in Credit A...
The dataset used in the paper is a reinforcement learning dataset, where the authors analyze the modularity of discrete-action reinforcement learning algorithms. -
Vehicle Routing Problem
The Vehicle Routing Problem (VRP) is a classic problem in combinatorial optimization. The problem is to find the shortest route that visits each node in a graph exactly once and... -
Newsvendor
The Newsvendor problem is a classic problem in inventory management. The problem is to determine the optimal order quantity to satisfy uncertain demand. -
ORL: Reinforcement Learning Benchmarks for Online Stochastic Optimization Pro...
Reinforcement Learning (RL) has achieved state-of-the-art results in domains such as robotics and games. We build on this previous work by applying RL algorithms to a selection... -
Comparison Datasets for Imitation Learning and Reinforcement Learning
Comparison datasets for Imitation Learning and Reinforcement Learning. -
RILe: Reinforced Imitation Learning
Reinforced Imitation Learning (RILe) dataset, which consists of expert demonstrations and noisy expert data. -
RL Unplugged
The RL Unplugged dataset, a benchmark for offline reinforcement learning, consisting of 20 tasks with varying difficulty levels. -
Explore2Offline
The dataset used in the paper for offline reinforcement learning, consisting of task-agnostic exploration data collected via curiosity-based intrinsic motivation. -
Multiple Domain Cyberspace Attack and Defense Game Model
The dataset used in the paper is a multiple domain cyberspace attack and defense game model based on reinforcement learning. -
Prioritized Sequence Experience Replay
Prioritized Sequence Experience Replay (PSER) is a novel framework for prioritizing sequences of transitions to both learn more efficiently and effectively. -
TorchCraft
The TorchCraft dataset is a collection of games played by a reinforcement learning agent, which can be used to train and evaluate reinforcement learning algorithms. -
Bootstrapped DQN
The Bootstrapped DQN dataset is a collection of 49 Atari games.