Paper Info
Title
Learning to Perform Physics Experiments via Deep Reinforcement Learning.
Abstract
When encountering novel objects, humans are able to infer a wide range of physical properties such as mass, friction and deformability by interacting with them in a goal driven way. This process of active interaction is in the same spirit as a scientist performing experiments to discover hidden facts. Recent advances in artificial intelligence have yielded machines that can achieve superhuman performance in Go, Atari, natural language processing, and complex control problems; however, it is not clear that these systems can rival the scientific intuition of even a young child. In this work we introduce a basic set of tasks that require agents to estimate properties such as mass and cohesion of objects in an interactive simulated environment where they can manipulate the objects and observe the consequences. We found that deep reinforcement learning methods can learn to perform the experiments necessary to discover such hidden properties. By systematically manipulating the problem difficulty and the cost incurred by the agent for performing experiments, we found that agents learn different strategies that balance the cost of gathering information against the cost of making mistakes in different situations. We also compare our learned experimentation policies to randomized baselines and show that the learned policies lead to better predictions.
Year
Venue
Field
2016
international conference on learning representations
Cohesion (chemistry),Intuition,Artificial intelligence,Error-driven learning,Mathematics,Machine learning,Reinforcement learning,Physics
DocType
Volume
Citations 
Journal
abs/1611.01843
1
PageRank 
References 
Authors
0.38
0
6
Name
Order
Citations
PageRank
Misha Denil139726.18
Pulkit Agrawal262724.55
Tejas Kulkarni3152.69
Tom Erez4102750.56
Peter Battaglia544222.63
Nando De Freitas63284273.68