Obstacle Tower: A Generalization Challenge in Vision, Control, and Planning
Open accessAbstract
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 in 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.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Proximal Policy Optimization Algorithms
Schulman, J., Wolski, F., Dhariwal, P., Radford, A., & Klimov, O. (2017) · arXiv · doi:10.48550/arxiv.1707.06347 · Cited by 10,625 · see citing works
Deep Reinforcement Learning That Matters
Henderson, P., Islam, R., Bachman, P., Pineau, J., Precup, D., & Meger, D. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11694 · Cited by 1,685 · see citing works
Unity: A General Platform for Intelligent Agents
Juliani, A., Berges, V.-P., Teng, E., Cohen, A., Harper, J., Elion, C., Goy, C., Gao, Y., Henry, H., Mattar, M., et al. (2018) · arXiv · doi:10.48550/arxiv.1809.02627 · Cited by 626 · cited 2× · see citing works
“The Obstacle Tower environment uses the Unity platform and ML-Agents Toolkit (Juliani et al. 2018).”
MethodSelf-citationLearning to reinforcement learn
Wang, J. X., Kurth-Nelson, Z., Tirumala, D., Soyer, H., Leibo, J. Z., Munos, R., Blundell, C., Kumaran, D., & Botvinick, M. (2016) · arXiv · doi:10.48550/arxiv.1611.05763 · Cited by 579 · see citing works
Exploration by Random Network Distillation
Burda, Y., Edwards, H., Storkey, A., & Klimov, O. (2018) · arXiv · doi:10.48550/arxiv.1810.12894 · Cited by 527 · see citing works
Machado, M. C., Bellemare, M. G., Talvitie, E., Veness, J., Hausknecht, M., & Bowling, M. (2018) · Journal of Artificial Intelligence Research · doi:10.1613/jair.5699 · Cited by 359 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Shortcut learning in deep neural networks
Geirhos, R., Jacobsen, J.-H., Michaelis, C., Zemel, R., Brendel, W., Bethge, M., & Wichmann, F. A. (2020) · Nature Machine Intelligence · doi:10.1038/s42256-020-00257-z · Cited by 2,224 · see citing works
Unity: A General Platform for Intelligent Agents
Juliani, A., Berges, V.-P., Teng, E., Cohen, A., Harper, J., Elion, C., Goy, C., Gao, Y., Henry, H., Mattar, M., et al. (2018) · arXiv · doi:10.48550/arxiv.1809.02627 · Cited by 626 · see citing works
“We also discuss the Obstacle Tower benchmark (Juliani et al., 2019) which serves as an example of the degree of environmental complexity achievable on Unity.”
BackgroundResultInfluentialSelf-citationA Survey of Zero-shot Generalisation in Deep Reinforcement Learning
Kirk, R., Zhang, A., Grefenstette, E., & Rocktäschel, T. (2023) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.14174 · Cited by 193 · see citing works
“%) there are well-established benchmarks for arcade styles (Cobbe et al., 2020a) and 3D environments (Juliani et al., 2019).”
BackgroundHuman-Timescale Adaptation in an Open-Ended Task Space
Adaptive Agent Team, Bauer, J., Baumli, K., Baveja, S., Behbahani, F., Bhoopchand, A., Bradley-Schmieg, N., Chang, M., Clay, N., Collister, A., et al. (2023) · arXiv · doi:10.48550/arxiv.2301.07608 · Cited by 19 · see citing works
“Indeed, in the past few years a series of challenging PCG environments have been proposed (Juliani et al., 2019; Cobbe et al., 2020; K¨uttler et al., 2020; Samvelyan et al., 2021; Chevalier-Boisvert et al., 2018; Hafner, 2022; Deitke et al., 2022), mostly focusing on testing and improving…”
BackgroundMeasuring Visual Generalization in Continuous Control from Pixels
Grigsby, J., & Qi, Y. (2020) · arXiv · doi:10.48550/arxiv.2010.06740 · Cited by 10 · see citing works
A Study of Global and Episodic Bonuses for Exploration in Contextual MDPs
Henaff, M., Jiang, M., & Raileanu, R. (2023) · arXiv · doi:10.48550/arxiv.2306.03236 · Cited by 1 · see citing works
“Examples of CMDPs include procedurally-generated environments (Chevalier-Boisvert et al., 2018; Samvelyan et al., 2021; K¨uttler et al., 2020; Juliani et al., 2019; Cobbe et al., 2020; Beattie et al., 2016; Hafner, 2021; Petrenko et al., 2021) or embodied AI tasks where the agent must generalize…”
Background
- Authors
- Juliani, A., Khalifa, A., Berges, V.-P., Harper, J., Teng, E., Henry, H., Crespi, A., Togelius, J., & Lange, D.
- Affiliations
- Unity Technologies
- New York University (US)
- Venue
- Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence
- Published
- 2019-08
- Pages
- 2684-2691
- OpenAlex
- W2914898814
- Cited by
- 93
- References
- 6
- Citations by year
- 2026: 1 · 2025: 4 · 2024: 4 · 2023: 13 · 2022: 10 · 2021: 16 · 2020: 33 · 2019: 10 · 2018: 2
- FWCI
- 6.60
- Type
- conference paper
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- International Joint Conference on Artificial Intelligence (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- OAR@UM (University of Malta) (submittedVersion, other-oa)
- arXiv (Cornell University)
- Funders
- National Science Foundation (1717324)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence in Games
- Physical Sciences › Computer Science › Artificial Intelligence › AI-based Problem Solving and Planning
- Keywords
- benchmark environments, procedural content generation, low-level control, high-level planning, sparse rewards, deep reinforcement learning, human performance comparison
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
