328 datasets found

The dataset used in the Temporally Layered Architecture (TLA) for adaptive, distributed and continuous control.

The dataset used in this paper is a multimedia search engine dataset, which is a Self-Learning Search Engine (SLSE) architecture based on reinforcement learning.

The dataset used in the paper is a set of waypoints and edges for planning.

The dataset used in the paper is a 2D environment where experiments are done.

Variational Quantum Circuits are being used as versatile Quantum Machine Learning models. Some empirical results exhibit an advantage in supervised and generative learning...

The dataset used in the paper is a replay buffer containing observations from a navigation task.

The Bank Heist environment is a 2D maze with four rooms, where the objective is to navigate to banks distributed across the four mazes.

The MNIST environment does not elicit any actions from an agent. Instead, the prediction network simply needs to learn one step mappings between pairs of MNIST handwritten digits.

The dataset used in the paper is a MuJoCo environment, with 13-states and 4-control inputs, nonlinear dynamics with polynomial dependency in the control inputs.

The corridor environment is a simple environment where the agent has to determine whether the rewarding cell (colored yellow) is at the top or bottom, based on the color of the...

Learning Adversarial Low-rank Markov Decision Processes with Unknown Transition and Full-information Feedback

The Robust MDPs problem is a Markov Decision Process problem where the goal is to find a policy π that maximizes the Value Function under worst-case transition dynamics.

The dataset used in the paper is a set of Pong variants, including Noisy, Black, White, Zoom, and others.

The dataset used in the paper is a set of 3D maze games, including Labyrinth and others.

Evolution of Rewards for Food and Motor Action by Simulating Birth and Death

Multimodal Query Suggestion with Multi-Agent Reinforcement Learning from Human Feedback

We investigate an infinite-horizon average reward Markov Decision Process (MDP) with delayed, composite, and partially anonymous reward feedback.

The dataset used in the paper is for the Double Tunnel environment, which is a safety-critical task.

A new Pong environment with a much higher degree of configurability than the current standard, including the ability to compete against a human opponent.

The dataset used in the paper is a collection of robot locomotion tasks with various constraints.