198 datasets found

Tags: Reinforcement Learning

Filter Results

  • Four Rooms

    The Four Rooms environment is a stochastic version of the classic Atari game Four Rooms. The environment has 104 states and 4 actions, and the agent can move in any of the 4...

  • Soft Actor-Critic With Integer Actions

    Reinforcement learning under integer actions by incorporating the Soft Actor-Critic (SAC) algorithm with an integer reparameterization.

  • PinBall

    The PinBall domain is a continuous state domain where the agent must navigate a ball through a set of obstacles to reach the main goal, with a four-dimensional state space...

  • GridBall

    The GridBall domain is similar to the FourRooms domain, but change to be more like a grid-world to facilitate visualization. The velocity components of the state are removed,...

  • FourRooms

    The FourRooms domain is a continuous state domain where the agent navigates a ball through a set of obstacles to reach the main goal. The environment uses a four-dimensional...

  • Kuka Object Manipulation Datasets

    The dataset is used for training and testing the Equivariant Diffuser for Generating Interactions (EDGI) algorithm.

  • Navigation and Manipulation Datasets

    The dataset is used for training and testing the Equivariant Diffuser for Generating Interactions (EDGI) algorithm.

  • Giraffe

    The dataset used in the paper is a collection of images of objects in 3D space, with multiple views of each object.

  • Nerf++

    The dataset used in the paper is a collection of images of objects in 3D space, with multiple views of each object.

  • NeRF-RL

    The dataset used in the paper is a collection of images of objects in 3D space, with multiple views of each object.

  • Robomimic Environment

    Robomimic environment consists of tasks such as lift, can, square, tool-hang, and transport.

  • D4RL Benchmark Suite

    D4RL benchmark suite consists of tasks such as locomotion, antmaze, adroit, and kitchen.

  • Random Walk dataset

    The dataset used in the paper is a collection of states sampled from a Markov Decision Process (MDP) using the random walk exploration method.

  • RND dataset

    The dataset used in the paper is a collection of states sampled from a Markov Decision Process (MDP) using the RND exploration method.

  • SMM dataset

    The dataset used in the paper is a collection of states sampled from a Markov Decision Process (MDP) using the SMM exploration method.

  • ChronoGEM dataset

    The dataset used in the paper is a collection of states sampled from a Markov Decision Process (MDP) using the ChronoGEM exploration method.

  • Gridworld Dataset

    The dataset used for the Gridworld tasks, consisting of 10K episodes of the agent following a uniform random policy.

  • Interaction Networks

    Interaction Networks: Using a Reinforcement Learner to train other Machine Learning algorithms

  • Towards Socially and Morally Aware RL agent: Reward Design With LLM

    The 2D Grid World environment with various items and consequences

  • Cartpole-v1

    The Cartpole-v1 environment is used to evaluate the performance of Federated Reinforcement Distillation (FRD) framework.
You can also access this registry using the API (see API Docs).