198 datasets found

The dataset used in this paper is a set of seven continuous control locomotion tasks implemented in Brax, derived from standard RL benchmarks.

The dataset used in the paper is a collection of tasks from OpenAI Gym, specifically Pong and Breakout.

The dataset used in the paper is a modified version of the HalfCheetah-v3 environment from the OpenAI gym.

The dataset used in the paper is a modified version of the FrozenLake-v0 environment from the OpenAI gym.

PPO Cartpole Task

The dataset used in the paper for testing the performance of the trained policy on the Euler equations.

The dataset used in the paper for training a recurrent spatio-temporal network for hyperbolic conservation laws.

The traffic light control dataset is used to evaluate the performance of reinforcement learning models in traffic light control.

The dataset used in the paper is not explicitly described, but it is mentioned that the authors used a hierarchical reward design framework to train policies in various...

The Four Rooms domain is a classic reinforcement learning environment where an agent must navigate a grid world to reach one of four goals.

Multimodality in World Models

The dataset is used for target detection and mapping problem, performed by a UAV (i.e., the agent), which autonomously navigates an indoor environment.

A Drone Swarm Search environment, based on PETTINGZOO, that is to be used in conjunction with multi-agent (or single-agent) reinforcement learning algorithms.

Value-function (VF) approximation is a central problem in Reinforcement Learning (RL). Classical non-parametric VF estimation suffers from the curse of dimensionality. As a...

The dataset used in the paper is the Multi-Stage Gridworld environment, which is a 3D environment that requires the agent to navigate through a gridworld to find a goal.

The dataset used in the paper is the Treasure Mountain environment, which is a 2D environment that requires the agent to navigate through a mountain to find a treasure.

The dataset used in the paper is an Inverted Pendulum dataset, which is a standard benchmark system in control and reinforcement learning.

The ProcGen Maze and Leaper environments are procedurally generated game environments used to benchmark reinforcement learning.

The MineRL-v0 dataset contains human demonstration data for tasks in Minecraft.

The MineRL BASALT competition dataset contains human demonstration data for four tasks in Minecraft.