pith. sign in

arxiv: 1610.05182 · v1 · pith:Z6B6YOMPnew · submitted 2016-10-17 · 💻 cs.RO · cs.AI

Learning and Transfer of Modulated Locomotor Controllers

classification 💻 cs.RO cs.AI
keywords architecturedimensionalnetworkspinaltasksaccesshigh-levellearning
0
0 comments X
read the original abstract

We study a novel architecture and training procedure for locomotion tasks. A high-frequency, low-level "spinal" network with access to proprioceptive sensors learns sensorimotor primitives by training on simple tasks. This pre-trained module is fixed and connected to a low-frequency, high-level "cortical" network, with access to all sensors, which drives behavior by modulating the inputs to the spinal network. Where a monolithic end-to-end architecture fails completely, learning with a pre-trained spinal module succeeds at multiple high-level tasks, and enables the effective exploration required to learn from sparse rewards. We test our proposed architecture on three simulated bodies: a 16-dimensional swimming snake, a 20-dimensional quadruped, and a 54-dimensional humanoid. Our results are illustrated in the accompanying video at https://youtu.be/sboPYvhpraQ

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. LatentMimic: Terrain-Adaptive Locomotion via Latent Space Imitation

    cs.RO 2026-04 unverdicted novelty 6.0

    LatentMimic decouples stylistic fidelity from geometric terrain constraints in quadruped locomotion via marginal latent divergence to a mocap prior and a dynamic replay buffer, yielding higher traversal success than m...

  2. Scalable Option Learning in High-Throughput Environments

    cs.LG 2025-08 unverdicted novelty 6.0

    SOL is a new hierarchical RL algorithm that reaches 35x higher throughput and outperforms flat agents when trained on 30 billion frames in NetHack while showing positive scaling.

  3. Learning to Solve a Rubik's Cube with a Dexterous Hand

    cs.RO 2019-07 unverdicted novelty 5.0

    Hierarchical RL combines a model-based cube solver with a model-free hand controller to solve Rubik's cubes in simulation, achieving 90.3% success on 1400 random scrambles.

  4. Neural Embedding for Physical Manipulations

    cs.LG 2019-07 unverdicted novelty 4.0

    Generative model with normalized pairwise distance constraint discovers output space topologies from sparse data and outperforms GANs and VAEs by avoiding mode collapse.