# Obstacle Tower: A Generalization Challenge in Vision, Control, and Planning

arXiv: https://arxiv.org/abs/1902.01378 · HTML: https://mlsanity.com/paper/1902.01378/

## Key facts

- Cited by 54 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Feb 2019.

## Built on by (most cited first, 30 of 54)

- [MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge](https://mlsanity.com/paper/2206.08853/) (2022)
- [Evolving Curricula with Regret-Based Environment Design](https://mlsanity.com/paper/2203.01302/) (2022)
- [A Survey of Zero-shot Generalisation in Deep Reinforcement Learning](https://mlsanity.com/paper/2111.09794/) (2021)
- [Human-Timescale Adaptation in an Open-Ended Task Space](https://mlsanity.com/paper/2301.07608/) (2023)
- [Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning](https://mlsanity.com/paper/2101.05265/) (2021)
- [SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2212.07489/) (2022)
- [Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Pot](https://mlsanity.com/paper/2107.06857/) (2021)
- [MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research](https://mlsanity.com/paper/2109.13202/) (2021)
- [Decoupling Value and Policy for Generalization in Reinforcement Learning](https://mlsanity.com/paper/2102.10330/) (2021)
- [Exploration via Elliptical Episodic Bonuses](https://mlsanity.com/paper/2210.05805/) (2022)
- [Contextualize Me -- The Case for Context in Reinforcement Learning](https://mlsanity.com/paper/2202.04500/) (2022)
- [Open-World Multi-Task Control Through Goal-Aware Representation Learning and Adaptive Horizon Prediction](https://mlsanity.com/paper/2301.10034/) (2023)
- [CORA: Benchmarks, Baselines, and Metrics as a Platform for Continual Reinforcement Learning Agents](https://mlsanity.com/paper/2110.10067/) (2021)
- [Alchemy: A benchmark and analysis toolkit for meta-reinforcement learning agents](https://mlsanity.com/paper/2102.02926/) (2021)
- [Look where you look! Saliency-guided Q-networks for generalization in visual Reinforcement Learning](https://mlsanity.com/paper/2209.09203/) (2022)
- [On the Importance of Exploration for Generalization in Reinforcement Learning](https://mlsanity.com/paper/2306.05483/) (2023)
- [RL-ViGen: A Reinforcement Learning Benchmark for Visual Generalization](https://mlsanity.com/paper/2307.10224/) (2023)
- [MineRL Diamond 2021 Competition: Overview, Results, and Lessons Learned](https://mlsanity.com/paper/2202.10583/) (2022)
- [The Generalization Gap in Offline Reinforcement Learning](https://mlsanity.com/paper/2312.05742/) (2023)
- [Odyssey: Empowering Minecraft Agents with Open-World Skills](https://mlsanity.com/paper/2407.15325/) (2024)
- [Quantifying the effects of environment and population diversity in multi-agent reinforcement learning](https://mlsanity.com/paper/2102.08370/) (2021)
- [A Study of Global and Episodic Bonuses for Exploration in Contextual MDPs](https://mlsanity.com/paper/2306.03236/) (2023)
- [Avalon: A Benchmark for RL Generalization Using Procedurally Generated Worlds](https://mlsanity.com/paper/2210.13417/) (2022)
- [DreamCraft: Text-Guided Generation of Functional 3D Environments in Minecraft](https://mlsanity.com/paper/2404.15538/) (2024)
- [A Review of Nine Physics Engines for Reinforcement Learning Research](https://mlsanity.com/paper/2407.08590/) (2024)
- [LECO: Learnable Episodic Count for Task-Specific Intrinsic Reward](https://mlsanity.com/paper/2210.05409/) (2022)
- [Affective Game Computing: A Survey](https://mlsanity.com/paper/2309.14104/) (2023)
- [HackAtari: Atari Learning Environments for Robust and Continual Reinforcement Learning](https://mlsanity.com/paper/2406.03997/) (2024)
- [TropeTwist: Trope-based Narrative Structure Generation](https://mlsanity.com/paper/2204.09672/) (2022)
- [Beyond The Rainbow: High Performance Deep Reinforcement Learning on a Desktop PC](https://mlsanity.com/paper/2411.03820/) (2024)

## Abstract (arXiv)

The rapid pace of recent research in AI has been driven in part by the presence of fast and challenging simulation environments. These environments often take the form of games; with tasks ranging from simple board games, to competitive video games. We propose a new benchmark - Obstacle Tower: a high fidelity, 3D, 3rd person, procedurally generated environment. An agent playing Obstacle Tower must learn to solve both low-level control and high-level planning problems in tandem while learning from pixels and a sparse reward signal. Unlike other benchmarks such as the Arcade Learning Environment, evaluation of agent performance in Obstacle Tower is based on an agent's ability to perform well on unseen instances of the environment. In this paper we outline the environment and provide a set of baseline results produced by current state-of-the-art Deep RL methods as well as human players. These algorithms fail to produce agents capable of performing near human level.