-
Multi-Agent Environment
The dataset used in the paper is a multi-agent environment where agents learn to coordinate their actions to achieve a common goal. The dataset is used to evaluate the proposed... -
Value Driven Representation for Human-in-the-Loop Reinforcement Learning
Interactive adaptive systems powered by Reinforcement Learning (RL) have many potential applications, such as intelligent tutoring systems. In such systems there is typically an... -
Exploration Coverage via Curiosity Driven Reinforcement Learning Agents
The dataset used in this paper for automatic exploration and testing of a 3D game scenario. -
Zero-Shot Policy Transfer with Disentangled Task Representation of Meta-Reinf...
Three simulated tasks and a challenging real-world robotic insertion task. -
Robot Grasping Dataset
The dataset used in this paper is a robot grasping dataset, where the robot learns to grasp objects in a simulated environment. -
Using Reinforcement Learning for the Three-Dimensional Loading Capacitated Ve...
The 3L-CVRP is a long-standing problem in the operations research literature. However, these existing approaches have two shortcomings. First, existing approaches are based on... -
Reinforcement learning for pursuit and evasion of microswimmers at low Reynol...
The dataset is used to study the pursuit and evasion of microswimmers at low Reynolds number. -
Data Informed Residual Reinforcement Learning for High-Dimensional Robotic Tr...
The dataset used in the paper is a high-dimensional robotic tracking control task. -
Large-Scale Study of Curiosity-Driven Learning
The dataset used in the paper is a collection of 54 standard benchmark environments, including the Atari game suite. -
Spacecraft Inspection Task
The dataset used in this paper for the spacecraft inspection task, which involves training a neural network controller (NNC) and run time assurance (RTA) algorithms. -
HalfCheetah and Walker2d
The dataset used in the paper is the HalfCheetah and Walker2d environments from the D4RL dataset. -
MineRL Diamond
The MineRL Diamond dataset is a large-scale dataset of Minecraft demonstrations, focusing on the development of sample-efficient reinforcement learning algorithms for mining... -
Mario AI Benchmark
The Mario AI benchmark dataset is used to evaluate the proposed approach to translate a policy trained by a Deep RL algorithm into a set of rules. -
OpenAI Gym and Roboschool
The dataset used in the paper is not explicitly described, but it is mentioned that the authors used OpenAI Gym and Roboschool environments. -
RealworldRL-Suite
The realworldrl-suite contains a set of real-world challenge wrappers across 8 DeepMind Control Suite tasks. -
gym-saturation
gym-saturation: a collection of OpenAI Gym environments for guiding saturation-style provers based on the given clause algorithm with reinforcement learning -
Leveraging Reward Gradients For Reinforcement Learning in Differentiable Phys...
A novel algorithm, Cross Entropy Analytic Policy Gradients (CE-APG), that is able to leverage analytic gradients to outperform state of the art deep reinforcement learning on a...
