Iterative Model-Based Reinforcement Learning Using Simulations in the Differentiable Neural Computer

Adeel Mufti, Svetlin Penkov, Subramanian Ramamoorthy

Research output: Contribution to conferencePaperpeer-review

Abstract

We propose a lifelong learning architecture, the Neural Computer Agent (NCA), where a Reinforcement Learning agent is paired with a predictive model of the environment learned by a Differentiable Neural Computer (DNC). The agent and DNC model are trained in conjunction iteratively. The agent improves its policy in simulations generated by the DNC model and rolls out the policy to the live environment, collecting experiences in new portions or tasks of the environment for further learning. Experiments in two synthetic environments show that DNC models can continually learn from pixels alone to simulate new tasks as they are encountered by the agent, while the agents can be successfully trained to solve the tasks using Proximal Policy Optimization entirely in simulations.
Original languageEnglish
Number of pages8
Publication statusE-pub ahead of print - 15 Jun 2019
EventWorkshop on Multi-Task and Lifelong Reinforcement Learning: Workshop at ICML, 15 June 2019, Long Beach - Long Beach, United States
Duration: 15 Jun 201915 Jun 2019
https://sites.google.com/view/mtlrl/

Workshop

WorkshopWorkshop on Multi-Task and Lifelong Reinforcement Learning
Abbreviated titleMTLRL
Country/TerritoryUnited States
CityLong Beach
Period15/06/1915/06/19
Internet address

Fingerprint

Dive into the research topics of 'Iterative Model-Based Reinforcement Learning Using Simulations in the Differentiable Neural Computer'. Together they form a unique fingerprint.

Cite this