198 datasets found

The dataset is used to train the Make-An-Agent model, a novel policy parameter generator that leverages the power of conditional diffusion models for behavior-to-policy generation.

The dataset used in this paper is a reinforcement learning benchmark problem, specifically the Bipedal Walker, Acrobot, and Continuous Lunar Lander tasks.

The BRIDGE dataset is a collection of 155 deterministic MDPs, each with a horizon of 100 time steps. The dataset is used to evaluate the performance of reinforcement learning...

The dataset used in this paper is the DeepMind Control Suite and PyBullet Environments.

The Arcade Learning Environment (ALE) is a lasting and indispensable element of the RL researcher’s toolbox. It is also the focus of our work. Since its inception, hundreds of...

The dataset used in the paper is a Visual Grid World Environment and the TextWorld domain.

Relay policy learning: Solving long-horizon tasks via imitation and reinforcement learning.

Mixed integer programming (MIP) problems with a linear objective, linear constraints, and integral constraints.

The dataset used in the paper is the Anthropic Helpfulness and Harmlessness dataset and the StackExchange dataset.

The dataset used in the paper is a set of MuJoCo environments with noise augmentation.

DMLab-30 is a benchmark for multitask reinforcement learning in partially observable environments.

The dataset used in this paper is the Car Racing game dataset, which consists of pixel frames of a car racing game.

The dataset used in this paper is the OpenAI Gym Environment dataset, which consists of various games and environments.

The dataset used in this paper is the Atari 2600 games dataset, which consists of 50 Atari 2600 games.

The dataset used in the paper for training and testing the DPO and PPO models.

The dataset used in the paper for training and testing the DPO and PPO models.

The HH-RLHF dataset is a human preference dataset for reinforcement learning from human feedback.

The dataset used in the paper for training and testing the DPO and PPO models.

The dataset used in the paper is the Cambridge restaurant domain from the PyDial toolkit.

The dataset used in the paper is a procedurally generated environment called ProcGen.