Timezone: »

 
Poster
Online Robust Policy Learning in the Presence of Unknown Adversaries
Aaron Havens · Zhanhong Jiang · Soumik Sarkar

Wed Dec 05 02:00 PM -- 04:00 PM (PST) @ Room 517 AB #128
in Wed Poster Session B »

The growing prospect of deep reinforcement learning (DRL) being used in cyber-physical systems has raised concerns around safety and robustness of autonomous agents. Recent work on generating adversarial attacks have shown that it is computationally feasible for a bad actor to fool a DRL policy into behaving sub optimally. Although certain adversarial attacks with specific attack models have been addressed, most studies are only interested in off-line optimization in the data space (e.g., example fitting, distillation). This paper introduces a Meta-Learned Advantage Hierarchy (MLAH) framework that is attack model-agnostic and more suited to reinforcement learning, via handling the attacks in the decision space (as opposed to data space) and directly mitigating learned bias introduced by the adversary. In MLAH, we learn separate sub-policies (nominal and adversarial) in an online manner, as guided by a supervisory master agent that detects the presence of the adversary by leveraging the advantage function for the sub-policies. We demonstrate that the proposed algorithm enables policy learning with significantly lower bias as compared to the state-of-the-art policy learning approaches even in the presence of heavy state information attacks. We present algorithm analysis and simulation results using popular OpenAI Gym environments.

Keywords: Reinforcement Learning · Hierarchical RL · Meta-Learning

Author Information

Aaron Havens (University of Illinois Urbana-Champaign)

I am a first-year graduate student in Aerospace Engineering working with Prof. Girish Chowdhary on robust decision making and control. I'm interested in making intelligent systems more adaptive and guaranteeing safety.

Zhanhong Jiang (Iowa State University)
Soumik Sarkar (Iowa State University)

More from the Same Authors