Shared Modular Recurrence in Contextual MDPs for Universal Morphology Control
cs.AI, cs.RO
Submitted: 2025-06-10
Updated: 2026-10-30
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- One Policy to Run Them All: an End-to-end Learning Approach to Multi-Embodiment Locomotion
- RT-1: Robotics Transformer for Real-World Control at Scale
- Scaling Cross-Embodied Learning: One Policy for Manipulation, Navigation, Locomotion and Aviation
- Contextual Markov Decision Processes
- GET-Zero: Graph Embodiment Transformer for Zero-shot Embodiment Generalization
- Proximal Policy Optimization Algorithms
- Body Transformer: Leveraging Robot Embodiment for Policy Learning
- Preparing for the Unknown: Learning a Universal Policy with Online System Identification
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents