Recent developments in multi-agent imitation learning have shown promising results for modeling the behavior of human drivers.
Deep reinforcement learning has seen great success across a breadth of tasks such as in game playing and robotic manipulation.
We present Vision-based Navigation with Language-based Assistance (VNLA), a grounded vision-language task where an agent with visual perception is guided via language to find objects in photorealistic indoor environments.
Recent work have shown how the optimal state-feedback, obtained as the solution to the Hamilton-Jacobi-Bellman equations, can be approximated for several nonlinear, deterministic systems by deep neural networks.
We propose an approach for mapping natural language instructions and raw observations to continuous control of a quadcopter drone.
We present foundations for using Model Predictive Control (MPC) as a differentiable policy class for reinforcement learning in continuous state and action spaces.