328 datasets found

The dataset used in this paper is a Cartpole system, where the objective is to prevent the pole from falling over by pushing the cart to the left or to the right.

The dataset used in this paper is a forest management problem, where the objective is to maintain an old forest for wildlife and make money by selling the cut wood.

The dataset used in this paper is the Cliff-walking task, which is a simple grid-based environment. The dataset is used to evaluate the performance of the Self-correcting...

The dataset used in this paper is the Grid-world task, which is a simple grid-based environment. The dataset is used to evaluate the performance of the Self-correcting...

A benchmark for evaluating task compositionality and long-horizon tasks through object manipulation, with language serving as the mechanism for goal specification.

The dataset used in this paper is a collection of state-action pairs generated by a pre-trained RL agent, used to train a self-supervised interpretable network (SSINet) to...

The dataset used in this paper is a collection of state-action pairs generated by a pre-trained RL agent, used to train a self-supervised interpretable network (SSINet) to...

The dataset used in this paper is a collection of state-action pairs generated by a pre-trained RL agent, used to train a self-supervised interpretable network (SSINet) to...

The dataset used in this paper is a collection of experiences of embodied agents in various environments, including a point mass, swimmer, and ant. The dataset is used to...

The dataset used in the paper is the Mujoco benchmarking continuous control tasks.

The dataset used in the paper is the Pendulum dataset, which is a continuous control problem.

The dataset used in the paper is a reinforcement learning dataset, specifically a Markov Decision Process (MDP) with a finite set of states and actions.

The dataset used in this paper is a collection of data points from a lunar lander, which is used to test the proposed APG algorithm for task switching.

The dataset used in the paper is a collection of real-world street networks.

The dataset used in the paper is a collection of 100-node irregular graphs.

The dataset used in the paper is a collection of 2D mazes, irregular graphs, and real-world street networks.

The dataset used in the paper is a reinforcement learning dataset, specifically the Mountain Car and Acrobot problems, and a Gridworld problem.

Scaling robot learning with semantically imagined experience.

Soft actor-critic algorithm with truly-satisfied inequality constraint

The dataset used in the paper is a simulated on-ramp merge scenario, with 3 vehicles involved. The dataset is used to train a Deep Reinforcement Learning model to learn an...