Exploiting Local Dynamics Regularity for Reusable Skills in Offline Hierarchical RL
Quick Take
The CARL algorithm enhances reusable skills in Hierarchical Reinforcement Learning by exploiting local dynamics regularity.
Key Points
- Focuses on local dynamics for skill reusability.
- Aligns contexts with required action sequences.
- Demonstrates improved performance on OGBench.
Article Excerpt
From source RSS / original summaryarXiv:2605. 26371v1 Announce Type: new Abstract: Hierarchical Reinforcement Learning (HRL) promises to solve long-horizon Reinforcement Learning (RL) tasks more efficiently than non-hierarchical counterparts by discovering and reusing temporally-extended skills. However, obtaining skills that are actually reusable remains an open challenge.
Towards this end, we focus on abstractions that exploit the intuition of local dynamics: local transitions in different global contexts require similar kinds of action sequences. By aligning these contexts with the action sequences they require, we are able to learn which skills to reuse and where to reuse them. In principle, this information should benefit many HRL algorithms, where high-level policies have to reason about the low-level skills they use.
The resulting algorithm CARL (Contrastive Action-based Representations for Reusable Local Control) shows both qualitative clustering of meaningful skills in complex humanoid environments and improved downstream performance on the OGBench benchmark when integrated with HIQL.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →From Prompts to Protocols: An AI Agent for Laboratory Automation
An AI agent integrates large language models for automating laboratory protocols, enhancing efficiency and accuracy.