Active perception in adversarial scenarios using maximum entropy deep reinforcement learning
© 2019 IEEE. We pose an active perception problem where an autonomous agent actively interacts with a second agent with potentially adversarial behaviors. Given the uncertainty in the intent of the other agent, the objective is to collect further evidence to help discriminate potential threats. The...
Main Authors: | Shen, Macheng, How, Jonathan P. |
---|---|
Other Authors: | Massachusetts Institute of Technology. Department of Aeronautics and Astronautics |
Format: | Article |
Language: | English |
Published: |
IEEE
2021
|
Online Access: | https://hdl.handle.net/1721.1/137865.2 |
Similar Items
-
Robust and Scalable Multiagent Reinforcement Learning in
Adversarial Scenarios
by: Shen, Macheng
Published: (2022) -
Scaling Up Multiagent Reinforcement Learning for Robotic Systems: Learn an Adaptive Sparse Communication Graph
by: Sun, Chuangchuang, et al.
Published: (2021) -
Certifiable Robustness to Adversarial State Uncertainty in Deep Reinforcement Learning
by: Everett, Michael, et al.
Published: (2021) -
Certifiable Robustness to Adversarial State Uncertainty in Deep Reinforcement Learning
by: Everett, Michael F, et al.
Published: (2021) -
Maximum Entropy Learning with Deep Belief Networks
by: Payton Lin, et al.
Published: (2016-07-01)