Domain Adversarial Reinforcement Learning
We consider the problem of generalization in reinforcement learning where visual aspects of the observations might differ, e.g. when there are different backgrounds or change in contrast, brightness, etc. We assume that our agent has access to only a few of the MDPs from the MDP distribution during training. The performance of the agent is then reported on new unknown test domains drawn from the distribution (e.g. unseen backgrounds). For this "zero-shot RL" task, we enforce invariance of the learned representations to visual domains via a domain adversarial optimization process. We empirically show that this approach allows achieving a significant generalization improvement to new unseen domains.
Code (0)
등록된 구현이 없습니다.
Tasks
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Similar Papers 제목 키워드 기반
Non-Robust Feature Mapping in Deep Reinforcement Learning
Adversarial perturbations to state observations can dramatically degrade the performance of deep reinforcement learning policies, and thus raise concerns regarding the robustness of deep reinforcement learning agents. A …
Atari GamesDeep Reinforcement Learningreinforcement-learningReinforcement Learning+1Adversarially Trained Neural Policies in the Fourier Domain
Reinforcement learning policies based on deep neural networks are vulnerable to imperceptible adversarial perturbations to their inputs, in much the same way as neural network image classifiers. Recent work has proposed …
Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)Domain Adaptation for Reinforcement Learning on the Atari
Deep reinforcement learning agents have recently been successful across a variety of discrete and continuous control tasks; however, they can be slow to train and require a large number of interactions with the environme…
continuous-controlContinuous ControlDeep Reinforcement LearningDomain Adaptation+4Adversarial observations in probabilistic State-Space Models for robust Reinforcement Learning
Decision-making under partial or adversarial observability requires accurate inference of the environment's latent state and its associated uncertainty. This work analyses adversarial attacks on linear probabilistic stat…
Reinforcement LearningFailure-Scenario Maker for Rule-Based Agent using Multi-agent Adversarial Reinforcement Learning and its Application to Autonomous Driving
We examine the problem of adversarial reinforcement learning for multi-agent domains including a rule-based agent. Rule-based algorithms are required in safety-critical applications for them to work properly in a wide ra…
Autonomous DrivingMulti-agent Reinforcement Learningreinforcement-learningReinforcement Learning+1