Mar 22, 2017 · This paper investigates the ability of neural networks to learn both LTL constraints and control policies in order to generate task plans in complex ...

In this work, we integrate Monte Carlo Tree Search with hierarchical neural net policies trained on expressive LTL specifications. We use reinforcement learning ...

In particular, self-driving cars are faced with a uniquely challenging task and motion planning problem that incorporates logical constraints with multiple ...

We formulate task and motion planning as a variant of Monte Carlo Tree Search over high-level options, each of which is represented by a learned control policy, ...

Mar 22, 2017 · This paper investigates the ability of neural networks to learn both LTL constraints and control policies in order to generate task plans in ...

This work integrates Monte Carlo Tree Search with hierarchical neural net policies trained on expressive LTL specifications to find deep neural networks.

In this work, we integrate Monte Carlo Tree Search with hierarchical neural net policies trained on expressive LTL specifications. We use reinforcement learning ...

We propose a methodology based on reinforcement learning that employs deep neural networks to learn low-level control policies as well as task-level option ...

Combining neural networks and tree search for task and motion planning in challenging environments. Paxton, C., Raman, V., Hager, G. D, & Kobilarov, ...

Combining neural networks and tree search for task and motion planning in challenging environments. C Paxton, V Raman, GD Hager, M Kobilarov.