Monday, June 5, 2023
SCIENMAG: Latest Science and Health News
No Result
View All Result
  • Login
  • HOME PAGE
  • BIOLOGY
  • CHEMISTRY AND PHYSICS
  • MEDICINE
    • Cancer
    • Infectious Emerging Diseases
  • SPACE
  • TECHNOLOGY
  • CONTACT US
  • HOME PAGE
  • BIOLOGY
  • CHEMISTRY AND PHYSICS
  • MEDICINE
    • Cancer
    • Infectious Emerging Diseases
  • SPACE
  • TECHNOLOGY
  • CONTACT US
No Result
View All Result
Scienmag - Latest science news from science magazine
No Result
View All Result
Home SCIENCE NEWS Technology and Engineering

Army research leads to more effective training model for robots

December 29, 2020
in Technology and Engineering
0
Share on FacebookShare on Twitter

IMAGE

Credit: (Photo illustration / U.S. Army)

ADELPHI, Md. — Multi-domain operations, the Army’s future operating concept, requires autonomous agents with learning components to operate alongside the warfighter. New Army research reduces the unpredictability of current training reinforcement learning policies so that they are more practically applicable to physical systems, especially ground robots.

These learning components will permit autonomous agents to reason and adapt to changing battlefield conditions, said Army researcher Dr. Alec Koppel from the U.S. Army Combat Capabilities Development Command, now known as DEVCOM, Army Research Laboratory.

The underlying adaptation and re-planning mechanism consists of reinforcement learning-based policies. Making these policies efficiently obtainable is critical to making the MDO operating concept a reality, he said.

According to Koppel, policy gradient methods in reinforcement learning are the foundation for scalable algorithms for continuous spaces, but existing techniques cannot incorporate broader decision-making goals such as risk sensitivity, safety constraints, exploration and divergence to a prior.

Designing autonomous behaviors when the relationship between dynamics and goals are complex may be addressed with reinforcement learning, which has gained attention recently for solving previously intractable tasks such as strategy games like go, chess and videogames such as Atari and Starcraft II, Koppel said.

Prevailing practice, unfortunately, demands astronomical sample complexity, such as thousands of years of simulated gameplay, he said. This sample complexity renders many common training mechanisms inapplicable to data-starved settings required by MDO context for the Next-Generation Combat Vehicle, or NGCV.

“To facilitate reinforcement learning for MDO and NGCV, training mechanisms must improve sample efficiency and reliability in continuous spaces,” Koppel said. “Through the generalization of existing policy search schemes to general utilities, we take a step towards breaking existing sample efficiency barriers of prevailing practice in reinforcement learning.”

Koppel and his research team developed new policy search schemes for general utilities, whose sample complexity is also established. They observed that the resulting policy search schemes reduce the volatility of reward accumulation, yield efficient exploration of an unknown domains and a mechanism for incorporating prior experience.

“This research contributes an augmentation of the classical Policy Gradient Theorem in reinforcement learning,” Koppel said. “It presents new policy search schemes for general utilities, whose sample complexity is also established. These innovations are impactful to the U.S. Army through their enabling of reinforcement learning objectives beyond the standard cumulative return, such as risk sensitivity, safety constraints, exploration and divergence to a prior.”

Notably, in the context of ground robots, he said, data is costly to acquire.

“Reducing the volatility of reward accumulation, ensuring one explores an unknown domain in an efficient manner, or incorporating prior experience, all contribute towards breaking existing sample efficiency barriers of prevailing practice in reinforcement learning by alleviating the amount of random sampling one requires in order to complete policy optimization,” Koppel said.

The future of this research is very bright, and Koppel has dedicated his efforts towards making his findings applicable for innovative technology for Soldiers on the battlefield.

“I am optimistic that reinforcement-learning equipped autonomous robots will be able to assist the warfighter in exploration, reconnaissance and risk assessment on the future battlefield,” Koppel said. “That this vision is made a reality is essential to what motivates which research problems I dedicate my efforts.”

The next step for this research is to incorporate the broader decision-making goals enabled by general utilities in reinforcement learning into multi-agent settings and investigate how interactive settings between reinforcement learning agents give rise to synergistic and antagonistic reasoning among teams.

According to Koppel, the technology that results from this research will be capable of reasoning under uncertainty in team scenarios.

###

This research, conducted in collaboration with Princeton University, University of Alberta and Google Deepmind, was a spotlight talk at NeurIPS 2020, one of the premiere conferences that fosters the exchange of neural information processing systems research in biological, technological, mathematical and theoretical aspects.

Media Contact
Jenna Brady
[email protected]

Original Source

https://www.army.mil/article/242079/army_research_leads_to_more_effective_training_model_for_robots

Tags: Computer ScienceResearch/DevelopmentRobotry/Artificial IntelligenceTechnology/Engineering/Computer Science
Share25Tweet16Share4ShareSendShare
  • Multiple Sclerosis Prevalence in Black Americans

    Multiple sclerosis more prevalent in Black Americans than previously thought

    70 shares
    Share 28 Tweet 18
  • Nearly 70% of private label avocado oil rancid or mixed with other oils

    65 shares
    Share 26 Tweet 16
  • Whales not to be counted on as ‘climate savers’: study

    65 shares
    Share 26 Tweet 16
  • University of Sydney launches innovative research fellowship scheme to tackle global challenges

    65 shares
    Share 26 Tweet 16
  • Phase 3 SWOG Cancer Research Network trial, led by a City of Hope researcher, demonstrates one-year progression-free survival in 94% of patients with Stage 3 or 4 classic Hodgkin lymphoma who received a checkpoint inhibitor combined with chemotherapy

    64 shares
    Share 26 Tweet 16
  • Null results research now published by major behavioral medicine journal

    782 shares
    Share 313 Tweet 196
ADVERTISEMENT

About us

We bring you the latest science news from best research centers and universities around the world. Check our website.

Latest NEWS

Null results research now published by major behavioral medicine journal

Why expensive wine appears to taste better

Multiple sclerosis more prevalent in Black Americans than previously thought

Subscribe to Blog via Email

Enter your email address to subscribe to this blog and receive notifications of new posts by email.

Join 206 other subscribers

© 2023 Scienmag- Science Magazine: Latest Science News.

No Result
View All Result
  • HOME PAGE
  • BIOLOGY
  • CHEMISTRY AND PHYSICS
  • MEDICINE
    • Cancer
    • Infectious Emerging Diseases
  • SPACE
  • TECHNOLOGY
  • CONTACT US

© 2023 Scienmag- Science Magazine: Latest Science News.

Welcome Back!

Login to your account below

Forgotten Password?

Retrieve your password

Please enter your username or email address to reset your password.

Log In