AdaptNet: Policy Adaptation for Physics-Based Character Control
Motivated by humans' ability to adapt skills in the learning of new ones, this paper presents AdaptNet, an approach for modifying the latent space of existing policies to allow new behaviors to be quickly learned from like tasks in comparison to learning from scratch. Building on top of a given reinforcement learning controller, AdaptNet uses a two-tier hierarchy that augments the original state embedding to support modest changes in a behavior and further modifies the policy network layers to make more substantive changes. The technique is shown to be effective for adapting existing physics-based controllers to a wide range of new styles for locomotion, new task targets, changes in character morphology and extensive changes in environment. Furthermore, it exhibits significant increase in learning efficiency, as indicated by greatly reduced training times when compared to training from scratch or using other approaches that modify existing policies. Code is available at https://motion-lab.github.io/AdaptNet.
Code (2)
Similar Papers 제목 키워드 기반
Multi-modal Representations for Fine-grained Multi-label Critical View of Safety Recognition
The Critical View of Safety (CVS) is crucial for safe laparoscopic cholecystectomy, yet assessing CVS criteria remains a complex and challenging task, even for experts. Traditional models for CVS recognition depend on vi…
Multi-class ClassificationBinary ClassificationUnsupervised domain adaptation semantic segmentation of high-resolution remote sensing imagery with invariant domain-level prototype memory
Semantic segmentation is a key technique involved in automatic interpretation of high-resolution remote sensing (HRS) imagery and has drawn much attention in the remote sensing community. Deep convolutional neural networ…
Domain AdaptationPseudo LabelPseudo Label FilteringSegmentation+2MaskAdapt: Learning Flexible Motion Adaptation via Mask-Invariant Prior for Physics-Based Characters
We present MaskAdapt, a framework for flexible motion adaptation in physics-based humanoid control. The framework follows a two-stage residual learning paradigm. In the first stage, we train a mask-invariant base policy …
Self-Adaptive Reconfigurable Arrays (SARA): Using ML to Assist Scaling GEMM Acceleration
With increasing diversity in Deep Neural Network(DNN) models in terms of layer shapes and sizes, the research community has been investigating flexible/reconfigurable accelerator substrates. This line of research has ope…
PFPN: Continuous Control of Physically Simulated Characters using Particle Filtering Policy Network
Data-driven methods for physics-based character control using reinforcement learning have been successfully applied to generate high-quality motions. However, existing approaches typically rely on Gaussian distributions …
continuous-controlContinuous Controlreinforcement-learningReinforcement Learning+1