Relational Deep Reinforcement Learning

06/05/2018
by   Vinicius Zambaldi, et al.
0

We introduce an approach for deep reinforcement learning (RL) that improves upon the efficiency, generalization capacity, and interpretability of conventional approaches through structured perception and relational reasoning. It uses self-attention to iteratively reason about the relations between entities in a scene and to guide a model-free policy. Our results show that in a novel navigation and planning task called Box-World, our agent finds interpretable solutions that improve upon baselines in terms of sample complexity, ability to generalize to more complex scenes than experienced during training, and overall performance. In the StarCraft II Learning Environment, our agent achieves state-of-the-art performance on six mini-games -- surpassing human grandmaster performance on four. By considering architectural inductive biases, our work opens new directions for overcoming important, but stubborn, challenges in deep RL.

READ FULL TEXT

page 2

page 5

page 6

page 7

page 13

research
08/13/2018

Visual Sensor Network Reconfiguration with Deep Reinforcement Learning

We present an approach for reconfiguration of dynamic visual sensor netw...
research
07/12/2020

Relational-Grid-World: A Novel Relational Reasoning Environment and An Agent Model for Relational Information Extraction

Reinforcement learning (RL) agents are often designed specifically for a...
research
06/04/2018

Relational inductive bias for physical construction in humans and machines

While current deep learning systems excel at tasks such as object classi...
research
09/21/2021

Graph-based Cluttered Scene Generation and Interactive Exploration using Deep Reinforcement Learning

We introduce a novel method to teach a robotic agent to interactively ex...
research
11/30/2020

IV-Posterior: Inverse Value Estimation for Interpretable Policy Certificates

Model-free reinforcement learning (RL) is a powerful tool to learn a bro...
research
01/24/2020

EgoMap: Projective mapping and structured egocentric memory for Deep RL

Tasks involving localization, memorization and planning in partially obs...
research
02/08/2021

Grid-to-Graph: Flexible Spatial Relational Inductive Biases for Reinforcement Learning

Although reinforcement learning has been successfully applied in many do...

Please sign up or login with your details

Forgot password? Click here to reset