Learning Invariances for Policy Generalization

Abstract

While recent progress has spawned very powerful machine learning systems, those agents remain extremely specialized and fail to transfer the knowledge they gain to similar yet unseen tasks. In this paper, we study a simple reinforcement learning problem and focus on learning policies that encode the proper invariances for generalization to different settings. We evaluate three potential methods for policy generalization: data augmentation, meta-learning and adversarial training. We find our data augmentation method to be effective, and study the potential of meta-learning and adversarial learning as alternative task-agnostic approaches.

arXiv comment7 pages, 1 figure

References in corpus (7)

• Adam: A Method for Stochastic Optimization
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• The Effectiveness of Data Augmentation in Image Classification using Deep Learning
• Asynchronous Methods for Deep Reinforcement Learning
• Fader Networks: Manipulating Images by Sliding Attributes
• Hybrid Reward Architecture for Reinforcement Learning
• Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning

Cited by in corpus (2)

• A Survey of Zero-shot Generalisation in Deep Reinforcement Learning
• Data-Efficient Reinforcement Learning with Self-Predictive Representations