Learning to Abstract Visuomotor Mappings using Meta-Reinforcement Learning
On the map: Deep reinforcement learning methods → Deep RL algorithms and representations
Abstract (arXiv)
We investigated the human capacity to acquire multiple visuomotor mappings for de novo skills. Using a grid navigation paradigm, we tested whether contextual cues implemented as different "grid worlds", allow participants to learn two distinct key-mappings more efficiently. Our results indicate that when contextual information is provided, task performance is significantly better. The same held true for meta-reinforcement learning agents that differed in whether or not they receive contextual information when performing the task. We evaluated their accuracy in predicting human performance in the task and analyzed their internal representations. The results indicate that contextual cues allow the formation of separate representations in space and time when using different visuomotor mappings, whereas the absence of them favors sharing one representation. While both strategies can allow learning of multiple visuomotor mappings, we showed contextual cues provide a computational advantage in terms of how many mappings can be learned.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods. Builds on 3 of its 29 references that are in the map. First posted on arXiv 5 Feb 2024.
Builds on
3 of 29 references.
References · 3
- 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,501
- 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,258
- 2022A2C is a special case of PPOcited by 16
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2021Generalization Through Hand-Eye Coordination: An Action Space for Learning Spatially-Invariant Visuomotor Control
- 2026Rethinking Implicit Spatial Representation in Visuomotor Policy Learning
- 2022Generalization with Lossy Affordances: Leveraging Broad Offline Data for Learning Visuomotor Tasks
- 2026Temporal Consistency Improves Generalization in Contextual Offline Meta Reinforcement Learning
- 2025Latent Policy Barrier: Learning Robust Visuomotor Policies by Staying In-Distribution
- 2025From Memories to Maps: Mechanisms of In-Context Reinforcement Learning in Transformers
- 2025Scalable Multi-Task Reinforcement Learning for Generalizable Spatial Intelligence in Visuomotor Agents
- 2026RoboTTT: Context Scaling for Robot Policies