Active Perception in Adversarial Scenarios using Maximum Entropy Deep Reinforcement Learning
arXiv:1902.05644
Abstract
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 technical challenges are the partial observability of the agent intent, the adversary modeling, and the corresponding uncertainty modeling. Note that an adversary agent may act to mislead the autonomous agent by using a deceptive strategy that is learned from past experiences. We propose an approach that combines belief space planning, generative adversary modeling, and maximum entropy reinforcement learning to obtain a stochastic belief space policy. By accounting for various adversarial behaviors in the simulation framework and minimizing the predictability of the autonomous agent's action, the resulting policy is more robust to unmodeled adversarial strategies. This improved robustness is empirically shown against an adversary that adapts to and exploits the autonomous agent's policy when compared with a standard Chance-Constraint Partially Observable Markov Decision Process robust approach.
References in corpus (8)
- Playing Atari with Deep Reinforcement Learning
- Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
- Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning
- Multiagent Bidirectionally-Coordinated Nets: Emergence of Human-level Coordination in Learning to Play StarCraft Combat Games
- Deep Reinforcement Learning from Self-Play in Imperfect-Information Games
- Regret Minimization for Partially Observable Deep Reinforcement Learning
- Decentralised Multi-Agent Reinforcement Learning for Dynamic and Uncertain Environments
- Learning in POMDPs with Monte Carlo Tree Search