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:
Autonomous agents
- Verified Autonomous Promo Codes for May 2024
Molly Higgins is a product/content reviewer and contributing producer at WIRED. She graduated with a bachelor’s degree in English from UCLA and an MFA in creative nonfiction writing from the ...
- Starknet to bring on AI agents that can carry out on-chain activity
Starknet is allowing Giza to put AI agents on its blockchain, which are slated to take over some on-chain tasks like optimizing yield.
- Agentic Artificial Intelligence: Looking Ahead to Potential Practical and Legal Issues When AI Gets Autonomous
Unlike autonomous vehicles, which have multiple cameras and sensors ... and other third parties and platforms with whom the AI agents might interact. Stay tuned!
- Bye-bye bots: Altera’s game-playing AI agents get backing from Eric Schmidt
Autonomous, AI-based players are coming to a gaming experience near you, and a new startup, Altera, is joining the fray to build this new guard of AI ...
- Composabl Launches Breakthrough No-Code UI Platform for Industrial Strength Autonomous Agents and Raises $4.25M
San Francisco, California--(Newsfile Corp. - May 7, 2024) - Composabl's ex-Microsoft founding team launches a breakthrough No-Code UI platform that enables engineers to directly teach AI agents to ...
Go deeper with Google Headlines on:
Autonomous agents
[google_news title=”” keyword=”autonomous agents” num_posts=”5″ blurb_length=”0″ show_thumb=”left”]
Go deeper with Bing News on:
Autonomous robots
- NASA wants to build a levitating robot train on the Moon
NASA has some really hair-brained plans, and I mean that in the best way possible. Despite facing some massive delays for its upcoming Artemis missions, … The post NASA wants to build a levitating ...
- LimX Dynamics’ W1 robot can stand, walk and roll on its hind ‘legs’
China’s LimX Dynamics has brought about a revolution in the field of robotics with the W1 quadruped robot being able to stand up and walk on its two feet. W1 was released just last year, and it was ...
- TerraClear pulls in $15M in funding for rock-clearing robots
TerraClear raises $15 million from existing investors to expand its sales channel and further commercialize its rock-clearing robots.
- Metro Chick-fil-A testing out delivery robots for a limited time
WOODSTOCK, Ga. — A metro Atlanta Chick-fil-A is testing out delivery robots. Chick-fil-A confirmed to Channel 2 Action News that a location in Woodstock will be testing out these autonomous robots for ...
- Exclusive: Wayve co-founder Alex Kendall on the autonomous future for cars and robots
U.K.-based autonomous vehicle startup Wayve started life as a software platform loaded into a tiny electric "car" called Renault Twizy. Festooned with cameras, the company's co-founders and PhD ...
Go deeper with Google Headlines on:
Autonomous robots
[google_news title=”” keyword=”autonomous robots” num_posts=”5″ blurb_length=”0″ show_thumb=”left”]