Continual curiosity-driven skill acquisition from high-dimensional video inputs for humanoid robots
Open accessThe DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.
Abstract
In the absence of external guidance, how can a robot learn to map the many raw pixels of high-dimensional visual inputs to useful action sequences? We propose here Continual Curiosity driven Skill Acquisition (CCSA). CCSA makes robots intrinsically motivated to acquire, store and reuse skills. Previous curiosity-based agents acquired skills by associating intrinsic rewards with world model improvements, and used reinforcement learning to learn how to get these intrinsic rewards. CCSA also does this, but unlike previous implementations, the world model is a set of compact low-dimensional representations of the streams of high-dimensional visual information, which are learned through incremental slow feature analysis. These representations augment the robot's state space with new information about the environment. We show how this information can have a higher-level (compared to pixels) and useful interpretation, for example, if the robot has grasped a cup in its field of view or not. After learning a representation, large intrinsic rewards are given to the robot for performing actions that greatly change the feature output, which has the tendency otherwise to change slowly in time. We show empirically what these actions are (e.g., grasping the cup) and how they can be useful as skills. An acquired skill includes both the learned actions and the learned slow feature representation. Skills are stored and reused to generate new observations, enabling continual acquisition of complex skills. We present results of experiments with an iCub humanoid robot that uses CCSA to incrementally acquire skills to topple, grasp and pick-place a cup, driven by its intrinsic motivation from raw pixel vision.
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
Training Products of Experts by Minimizing Contrastive Divergence
Hinton, G. E. (2002) · Neural Computation · doi:10.1162/089976602760128018 · Cited by 4,879
Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning
Sutton, R. S., Precup, D., & Singh, S. (1999) · Artificial Intelligence · doi:10.1016/s0004-3702(99)00052-1 · Cited by 3,119
Formal theory of creativity, fun, and intrinsic motivation (1990–2010)
Schmidhuber, J. (2010) · IEEE Transactions on Autonomous Mental Development · doi:10.1109/tamd.2010.2056368 · Cited by 747
Self-citationCHILD: A First Step Towards Continual Learning
Ring, M. B. (1997) · Machine Learning · doi:10.1023/a:1007331723572 · Cited by 143
Learning tactile skills through curious exploration
Pape, L., Oddo, C. M., Controzzi, M., Cipriani, C., Förster, A., Carrozza, M. C., & Schmidhuber, J. (2012) · Frontiers in Neurorobotics · doi:10.3389/fnbot.2012.00006 · Cited by 51 · cited 1×
“Pape et al. [25] proposed a method for autonomous acquisition of tactile skills on a biomimetic robot finger, through curiosity-driven reinforcement learning. models on this low-level experience, which it later uses to generate plans of actions.”
MethodSelf-citation
Cited by
Deep Reinforcement Learning: An Overview
Li, Y. (2017) · arXiv · doi:10.48550/arxiv.1701.07274 · Cited by 762
Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents
Zhang, J., Hu, S., Lu, C., Lange, R., & Clune, J. (2025) · arXiv · doi:10.48550/arxiv.2505.22954 · Cited by 344
Towards a science of integrated AI and Robotics
Rajan, K., & Saffiotti, A. (2017) · Artificial Intelligence · doi:10.1016/j.artint.2017.03.003 · Cited by 180
Some Considerations on Learning to Explore via Meta-Reinforcement Learning
Stadie, B. C., Yang, G., Houthooft, R., Chen, X., Duan, Y., Wu, Y., Abbeel, P., & Sutskever, I. (2018) · arXiv · doi:10.48550/arxiv.1803.01118 · Cited by 74
“eedy exploration [15], or perhaps a simple scheme like Boltzmann exploration [6]. As a result of these shortcomings, a variety of new approaches to exploration in deep RL have recently been suggested [34, 9, 31, 18, 4, 19, 17, 8, 23, 17, 8, 26, 25, 32, 33, 12, 24]. In spite of these numerous efforts, the problem of ex…”
BackgroundGeneral intelligence requires rethinking exploration
Jiang, M., Rocktäschel, T., & Grefenstette, E. (2022) · arXiv · doi:10.48550/arxiv.2211.07819 · Cited by 17
Metadata
- Authors
- Kompella, V. R., Stollenga, M., Luciw, M., & Schmidhuber, J.
- Venue
- Artificial Intelligence
- Publisher
- Elsevier BV
- Published
- 2017-06
- Volume
- 247
- Pages
- 313-335
- ISSN
- 0004-3702 (ISSN-L)
- OpenAlex
- W2083954950
- Cited by
- 52
- References
- 5
- FWCI
- 6.26
- Type
- journal article
- Language
- en
- Open access
- hybrid
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
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.