Rotation, Translation, and Cropping for Zero-Shot Generalization

Abstract

Deep Reinforcement Learning (DRL) has shown impressive performance on domains with visual inputs, in particular various games. However, the agent is usually trained on a fixed environment, e.g. a fixed number of levels. A growing mass of evidence suggests that these trained models fail to generalize to even slight variations of the environments they were trained on. This paper advances the hypothesis that the lack of generalization is partly due to the input representation, and explores how rotation, cropping and translation could increase generality. We show that a cropped, translated and rotated observation can get better generalization on unseen levels of two-dimensional arcade games from the GVGAI framework. The generality of the agents is evaluated on both human-designed and procedurally generated levels.

arXiv commentIEEE Conference on Games 2020 Full Paper

References in corpus (12)

• IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
• Recurrent World Models Facilitate Policy Evolution
• Emergent Tool Use From Multi-Agent Autocurricula
• Reinforcement Learning with Augmented Data
• Quantifying Generalization in Reinforcement Learning
• Leveraging Procedural Generation to Benchmark Reinforcement Learning
• Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels
• Illuminating Generalization in Deep Reinforcement Learning through Procedural Level Generation
• ViZDoom Competitions: Playing Doom from Pixels
• Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneck
• Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learning
• Natural Environment Benchmarks for Reinforcement Learning

Cited by in corpus (6)

• Automatic Data Augmentation for Generalization in Deep Reinforcement Learning
• Learning with AMIGo: Adversarially Motivated Intrinsic Goals
• The NetHack Learning Environment
• Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning
• Decoupling Value and Policy for Generalization in Reinforcement Learning
• Active Reinforcement Learning over MDPs