328 datasets found

The Newsvendor problem is a classic problem in inventory management. The problem is to determine the optimal order quantity to satisfy uncertain demand.

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...

The Cart-Pole environment is a classic control problem in reinforcement learning, where an agent learns to balance a pole using a cart.

Comparison datasets for Imitation Learning and Reinforcement Learning.

Reinforced Imitation Learning (RILe) dataset, which consists of expert demonstrations and noisy expert data.

The RL Unplugged dataset, a benchmark for offline reinforcement learning, consisting of 20 tasks with varying difficulty levels.

The dataset used in the paper for offline reinforcement learning, consisting of task-agnostic exploration data collected via curiosity-based intrinsic motivation.

The dataset used in the paper is a multiple domain cyberspace attack and defense game model based on reinforcement learning.

Prioritized Sequence Experience Replay (PSER) is a novel framework for prioritizing sequences of transitions to both learn more efficiently and effectively.

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.

The Bootstrapped DQN dataset is a collection of 49 Atari games.

The Incentivizing Exploration in Atari dataset is a collection of 49 Atari games.

The Arcade Learning Environment (ALE) dataset is a collection of 49 Atari games.

The dataset used in the paper is a grid-world environment, which is a discrete MDP. The environment has four walls, some obstacles, a start-state and a reward-state. The goal of...

MinAtar is a new evaluation platform designed to allow for more thorough and reproducible experiments in reinforcement learning.

The dataset used in the paper is a real-world traffic signal control dataset, which includes 48 intersections in the New York road network.

The dataset used in the paper is a real-world traffic signal control dataset, which includes 12 intersections in the Jinan road network.

The dataset used in the paper is a real-world traffic signal control dataset, which includes 33 traffic signals in the Shenzhen road network.

The dataset used in the paper is a real-world traffic signal control dataset, which includes 80 red-light cameras and 16 monitoring cameras in a hour. There are 1,775 valid...

The dataset used in the Efficient Reward Poisoning Attacks on Online Deep Reinforcement Learning paper.