198 datasets found

The dataset used in the paper is Google Research Football (GRF) environment.

D4RL benchmark dataset, which consists of four offline logging datasets, collected by different one or mixed behavior policies.

The dataset used in the ACE algorithm for continuous control problems.

D4RL datasets for maze2d-umaze, maze2d-medium, maze2d-large, antmaze-umaze, antmaze-medium, antmaze-large, parking, soccer-sim, and soccer-physical tasks

The dataset used in this paper is the AndroidEnv environment.

The dataset used in this paper is the Playhouse and AndroidEnv environments.

The dataset contains data from human-level control through deep reinforcement learning.

The authors propose a novel approach that incorporates parameter-efficient tuning to better optimize control tokens, thus benefitting controllable generation.

The dataset used in the paper is a real-world dataset for influence maximization, which is a combinatorial optimization problem.

The dataset used in the paper is a collection of simulated environments, including blockworld, canada, cart, cartpole, cartpoleBalance, cartpoleParallelDouble,...

The dataset used in the paper is a reinforcement learning environment, specifically Cartpole, Canniballs, and a custom minigame in the StarCraft II Learning Environment.

The dataset used in this paper is the Atari Learning Environment (ALE) dataset, which consists of 15 Atari video games.

The dataset used in the paper is not explicitly described, but it is mentioned that the authors used several continuous control environments from the OpenAI Gym.

The dataset used in the paper is a simple gridworld domain with pixel-based states.

The dataset used in the paper is not explicitly described, but it is mentioned that it is a comprehensive set of possible states of the environment.

The dataset used in the paper is the Toxic-DPO dataset, which is used for reinforcement learning from human feedback.

The dataset used in the paper is the Anthropic-HH-RLHF dataset, which is used for reinforcement learning from human feedback.

The CartPole problem is a classic control problem in robotics and control theory. It is a simple, continuous control problem where a pole is attached to a mass on a cart, and...