Reflex: Reinforcement Learning with Reflection Symmetry Exploitation in State-Based Continuous Control
The paper introduces Reflex, a new approach to reinforcement learning that utilizes reflection symmetry in state-based continuous control tasks. This method aims to improve sample efficiency by integrating reflection symmetry into policy learning. The authors demonstrate that Reflex outperforms standard baselines when evaluated on various benchmarks.
- ▪Reflex leverages group-invariant Markov Decision Processes to enhance sample efficiency in reinforcement learning.
- ▪The paper focuses on state-based continuous control tasks and introduces two types of reflection: axial and bilateral.
- ▪Reflex integrates with both on-policy and off-policy reinforcement learning algorithms, showing superior performance in tests.
arXiv cs.AI files mainly under ai research. We currently carry 1,128 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | arXiv cs.AI |
| Canonical URL | https://arxiv.org/abs/2605.23415 |
| Publication time | Mon, 25 May 2026 00:00:00 -0400 |
| Retrieval time | 2026-05-25T04:07:35.648Z |
| Last seen | 2026-05-25T04:07:35.648Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | piD0M0uMiwWV |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Machine Learning arXiv:2605.23415 (cs) [Submitted on 22 May 2026] Title:Reflex: Reinforcement Learning with Reflection Symmetry Exploitation in State-Based Continuous Control Authors:Shuai Zhen, Yifan Zhang, Yuling Wang, Yanhua Yu View a PDF of the paper titled Reflex: Reinforcement Learning with Reflection Symmetry Exploitation in State-Based Continuous Control, by Shuai Zhen and 3 other authors View PDF HTML (experimental) Abstract:Reinforcement learning has long struggled with poor sample efficiency. One promising approach to mitigate this problem is leveraging group-invariant Markov Decision Processes ($G$-invariant MDPs).
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
