# Rotation, Translation, and Cropping for Zero-Shot Generalization

arXiv: https://arxiv.org/abs/2001.09908 · HTML: https://mlsanity.com/paper/2001.09908/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Jan 2020.

## Built on by (most cited first, 24 of 24)

- [Collaborating with Humans without Human Data](https://mlsanity.com/paper/2110.08176/) (2021)
- [Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning](https://mlsanity.com/paper/2101.05265/) (2021)
- [Decoupling Value and Policy for Generalization in Reinforcement Learning](https://mlsanity.com/paper/2102.10330/) (2021)
- [On the Importance of Exploration for Generalization in Reinforcement Learning](https://mlsanity.com/paper/2306.05483/) (2023)
- [The Generalization Gap in Offline Reinforcement Learning](https://mlsanity.com/paper/2312.05742/) (2023)
- [Explore to Generalize in Zero-Shot RL](https://mlsanity.com/paper/2306.03072/) (2023)
- [Learning Task-relevant Representations for Generalization via Characteristic Functions of Reward Sequence Distributions](https://mlsanity.com/paper/2205.10218/) (2022)
- [Path of Destruction: Learning an Iterative Level Generator Using a Small Dataset](https://mlsanity.com/paper/2202.10184/) (2022)
- [Warmth and competence in human-agent cooperation](https://mlsanity.com/paper/2201.13448/) (2022)
- [The Overcooked Generalisation Challenge: Evaluating Cooperation with Novel Partners in Unknown Environments Using Unsupervised Environment Design](https://mlsanity.com/paper/2406.17949/) (2024)
- [Mutation Models: Learning to Generate Levels by Imitating Evolution](https://mlsanity.com/paper/2206.05497/) (2022)
- [Tuning Mixed Input Hyperparameters on the Fly for Efficient Population Based AutoRL](https://mlsanity.com/paper/2106.15883/) (2021)
- [PCGRL+: Scaling, Control and Generalization in Reinforcement Learning Level Generators](https://mlsanity.com/paper/2408.12525/) (2024)
- [Transfer Dynamics in Emergent Evolutionary Curricula](https://mlsanity.com/paper/2203.10941/) (2022)
- [Improving Generalization on the ProcGen Benchmark with Simple Architectural Changes and Scale](https://mlsanity.com/paper/2410.10905/) (2024)
- [Learning Generalizable Representations for Reinforcement Learning via Adaptive Meta-learner of Behavioral Similarities](https://mlsanity.com/paper/2212.13088/) (2022)
- [ARLO: A Framework for Automated Reinforcement Learning](https://mlsanity.com/paper/2205.10416/) (2022)
- [Equivariant Data Augmentation for Generalization in Offline Reinforcement Learning](https://mlsanity.com/paper/2309.07578/) (2023)
- [Provable Zero-Shot Generalization in Offline Reinforcement Learning](https://mlsanity.com/paper/2503.07988/) (2025)
- [Predicting Personas Using Mechanic Frequencies and Game State Traces](https://mlsanity.com/paper/2203.13351/) (2022)
- [Adaptive Data Exploitation in Deep Reinforcement Learning](https://mlsanity.com/paper/2501.12620/) (2025)
- [Active Reinforcement Learning over MDPs](https://mlsanity.com/paper/2108.02323/) (2021)
- [Do Agents Dream of Electric Sheep?: Improving Generalization in Reinforcement Learning through Generative Learning](https://mlsanity.com/paper/2403.07979/) (2024)
- [Grounded Joint-Attention Other-Play for Zero-Shot Coordination](https://mlsanity.com/paper/2610.06025/) (2026)

## Abstract (arXiv)

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.