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.
The Latest Updates from Bing News & Google News
Go deeper with Bing News on:
- Packing safety intelligence into robots’ AI brainson April 12, 2021 at 3:00 am
We’re finding that smart robots don’t necessarily have the common sense needed to keep human beings out of harm’s way.
- P1.4M worth of illegal drugs seized in Cotabato City and Maguindanaoon April 10, 2021 at 4:59 pm
COTABATO CITY – Anti-narcotics agents in the Bangsamoro arrested seven people ... regional director of the Philippine Drug Enforcement Authority (PDEA) in the Bangsamoro Autonomous Region in Muslim ...
- Microsoft open-sources tool to use AI in simulated attackson April 9, 2021 at 11:50 pm
Microsoft released CyberBattleSim, an open source toolkit to let researchers create attack simulations and use AI to develop network defenses.
- PDEA-BARMM nets P1.4-M drugs in Maguindanao, Cotabato City opson April 9, 2021 at 9:19 pm
An anti-narcotics agent accounts for the items seized from the Zainal couple ... the Philippine Drug Enforcement Agency - Bangsamoro Autonomous Region in Muslim Mindanao (PDEA-BARMM) has reported.
- New documentary reveals “inside agents” supporting terrorism, separatism in Xinjiangon April 2, 2021 at 4:19 am
The fourth documentary on the anti-terrorism fight in Northwest China's Xinjiang Uyghur Autonomous Region was released on Friday. It focuses on the region's terrorist activities, "two-faced inside ...
Go deeper with Google Headlines on:
Go deeper with Bing News on:
- Domino's Pizza pilots driverless delivery with Nuro autonomous car in Houstonon April 12, 2021 at 7:58 am
A Domino's spokeswoman said that the company doesn't have an end date for the pilot program yet. The R2 robot is the first completely autonomous on-road delivery vehicle without any occupants to ...
- Domino’s is putting its delivery robot to workon April 12, 2021 at 7:56 am
Some folks in Houston could get their pizzas by robot starting this week. Domino’s Pizza and the autonomous vehicle maker Nuro will start testing their robotic pizza delivery vehicle for live ...
- Domino's is launching autonomous pizza delivery with a tiny self-driving caron April 12, 2021 at 7:53 am
Domino's will start delivering pizzas with autonomous self-driving robots from Nuro, the companies announced. Load Error The program will be available to certain customers in Houston, Texas using Nuro ...
- Domino’s starts making autonomous pizza deliverieson April 12, 2021 at 7:42 am
If you order a pizza from Domino’s in Houston, a robot might drop off your dinner. The company will this week start making autonomous deliveries with the help of Nuro’s R2 robot, almost two years ...
- Domino's, Nuro To Start Autonomous Pizza Delivery In Houstonon April 12, 2021 at 7:29 am
... autonomous vehicle startup Nuro are launching autonomous pizza delivery in Houston, this week. Following the launch, some Domino's customers in Houston can have a pizza delivered by Nuro's R2 ...