GridToPix: Training Embodied Agents with Minimal Supervision
The DOI matches its Crossref record; 29 of the 29 references it cites were found in a registry or an index.
Abstract
While deep reinforcement learning (RL) promises freedom from hand-labeled data, great successes, especially for Embodied AI, require significant work to create supervision via carefully shaped rewards. Indeed, without shaped rewards, i.e., with only terminal rewards, present-day Embodied AI results degrade significantly across Embodied AI problems from single-agent Habitat-based PointGoal Navigation (SPL drops from 55 to 0) and two-agent AI2-THOR-based Furniture Moving (success drops from 58% to 1%) to three-agent Google Football-based 3 vs. 1 with Keeper (game score drops from 0.6 to 0.1). As training from shaped rewards doesn’t scale to more realistic tasks, the community needs to improve the success of training with terminal rewards. For this we propose GRIDTOPIX: 1) train agents with terminal rewards in gridworlds that generically mirror Embodied AI environments, i.e., they are independent of the task; 2) distill the learned policy into agents that reside in complex visual worlds. Despite learning from only terminal rewards with identical models and RL algorithms, GRIDTOPIX significantly improves results across tasks: from PointGoal Navigation (SPL improves from 0 to 64) and Furniture Moving (success improves from 1% to 25%) to football gameplay (game score improves from 0.1 to 0.6). GRIDTOPIX even helps to improve the results of shaped reward training.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Histograms of Oriented Gradients for Human Detection
Dalal, N., & Triggs, B. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.177 · Cited by 33,584
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
A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play
Silver, D., Hubert, T., Schrittwieser, J., Antonoglou, I., Lai, M., Guez, A., Lanctot, M., Sifre, L., Kumaran, D., Graepel, T., et al. (2018) · Science · doi:10.1126/science.aar6404 · Cited by 3,562 · cited 2×
“If present-day RL algorithms have been successful in other domains (particularly ones requiring less visual processing [62, 61, 16]), why do they struggle for Embodied AI? Our hypothesis: this struggle is due to the need for embodied agents to learn to plan and perceive simultaneously.”
BackgroundA Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning
Ross, S., Gordon, G. J., & Bagnell, J. A. (2018) · Carnegie Mellon University · doi:10.1184/r1/6550949 · Cited by 1,941
Matterport3D: Learning from RGB-D Data in Indoor Environments
Chang, A., Dai, A., Funkhouser, T., Halber, M., Niebner, M., Savva, M., Song, S., Zeng, A., & Zhang, Y. (2017) · 2017 International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2017.00081 · Cited by 1,858
Curiosity-Driven Exploration by Self-Supervised Prediction
Pathak, D., Agrawal, P., Efros, A. A., & Darrell, T. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2017.70 · Cited by 1,815 · cited 1×
“A number of approaches have been proposed: curiosity as intrinsic motivation for exploring diverse states [53], using hindsight to reinterpret “failed” trajectories [3], curriculum learning [8, 22], self-play [62, 6], and learning to shape rewards [66, 51, 25].”
BackgroundScheduled Sampling for Sequence Prediction with Recurrent Neural Networks
Bengio, S., Vinyals, O., Jaitly, N., & Shazeer, N. (2015) · arXiv · doi:10.48550/arxiv.1506.03099 · Cited by 1,621
Target-driven visual navigation in indoor scenes using deep reinforcement learning
Zhu, Y., Mottaghi, R., Kolve, E., Lim, J. J., Gupta, A., Fei-Fei, L., & Farhadi, A. (2017) · 2017 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2017.7989381 · Cited by 1,533 · cited 1×
“rewards1 [84], the pursuit of increasingly capable agents has steered us towards employing large amounts of human supervision [60, 2, 65, 28, 37], reward shaping [75, 67], and task-specific architectures [12, 54].”
BackgroundHabitat: A Platform for Embodied AI Research
Savva, M., Kadian, A., Maksymets, O., Zhao, Y., Wijmans, E., Jain, B., Straub, J., Liu, J., Koltun, V., Malik, J., et al. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00943 · Cited by 1,237 · cited 9×
“In this work, optimal actions can be easily computed for the popular Point Navigation task [58].”
BackgroundMethodInfluentialAnderson, P., Wu, Q., Teney, D., Bruce, J., Johnson, M., Sunderhauf, N., Reid, I., Gould, S., & van den Hengel, A. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00387 · Cited by 1,187
Cited by
Simple but Effective: CLIP Embeddings for Embodied AI
Khandelwal, A., Weihs, L., Mottaghi, R., & Kembhavi, A. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01441 · Cited by 172
“There have been two challenges for RoboTHOR OBJECTNAV (in 2020 and 2021), as well as several prior works that have used RoboTHOR OBJECTNAV as a testbed for reinforcement and imitation learning methodologies [12, 32] and for studying model robustness [6].”
MethodSelf-citationAffordances from Human Videos as a Versatile Representation for Robotics
Bahl, S., Mendonca, R., Chen, L., Jain, U., & Pathak, D. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01324 · Cited by 119
“Exploration meth-ods are usually guided by intrinsic rewards that are self-generated by the robotic agent, and are not specific to any task [9, 49, 51, 64, 73, 86, 90, 93, 98, 117].”
BackgroundSelf-citationScene Graph Contrastive Learning for Embodied Navigation
Singh, K. P., Salvador, J., Weihs, L., & Kembhavi, A. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00999 · Cited by 23
Self-citationHabitat 3.0: A Co-Habitat for Humans, Avatars, and Robots
Puig, X., Undersander, E., Szot, A., Cote, M. D., Yang, T.-Y., Partsey, R., Desai, R., Clegg, A. W., Hlavac, M., Min, S. Y., et al. (2023) · arXiv · doi:10.48550/arxiv.2310.13724 · Cited by 15
“2021) study heterogeneous agents with different capabilities towards solving a shared task.”
BackgroundSelf-citationPhone2Proc: Bringing Robust Robots into Our Chaotic World
Deitke, M., Hendrix, R., Farhadi, A., Ehsani, K., & Kembhavi, A. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.00932 · Cited by 11
“Other methods for navigation use scene priors [69], meta-learning [64], paired grid world environments [27], scene memory transformers [19], passive videos of roaming in a scene as a training cue [24] and expert human trajectories for imitation learning [49].”
MethodSelf-citation
Metadata
- Authors
- Jain, U., Liu, I.-J., Lazebnik, S., Kembhavi, A., Weihs, L., & Schwing, A.
- Venue
- 2021 IEEE/CVF International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2021-10
- Pages
- 15121-15131
- OpenAlex
- W3162127726
- Cited by
- 14
- References
- 29
- FWCI
- 1.36
- Type
- conference paper
- Language
- en
- Open access
- closed
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: GridToPix: Training Embodied Agents with Minimal Supervision. https://app.cochat.ai/papers/10.1109/iccv48922.2021.01486
- The paper
- Jain, U., Liu, I.-J., Lazebnik, S., Kembhavi, A., Weihs, L., & Schwing, A. (2021). GridToPix: Training Embodied Agents with Minimal Supervision. 2021 IEEE/CVF International Conference on Computer Vision (ICCV). https://doi.org/10.1109/iccv48922.2021.01486
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.