On The Convergence And Stability Of Upsidedown Reinforcement Learning Goalconditioned Supervised Learning And Online Decision Transformers
ASecurity**arXiv ID:** 2502.05672 **Authors:** Miroslav Štrupl, Oleg Szehr, Francesco Faccio, Dylan R. Ashley, Rupesh Kumar Srivastava, Jürgen Schmidhuber **Published:** 2025-02-08T19:26:22Z **Abstract:** This article provides a rigorous analysis of convergence and stability of Episodic Upside-Down Reinforcement Learning, Goal-Conditioned Supervised Learning and Online Decision Transformers. These algorithms performed competitively across various benchmarks, from games to robotic tasks, but their theo...
- 3 stars
- 0 votes
- 0 copies
- 4 views
- Added September 11, 2026
Security analysis
100/100npx -y skills add hiyenwong/ai_collection --skill on-the-convergence-and-stability-of-upsidedown-reinforcement-learning-goalconditioned-supervised-learning-and-online-decision-transformers --agent claude-codeAre you the author of On The Convergence And Stability Of Upsidedown Reinforcement Learning Goalconditioned Supervised Learning And Online Decision Transformers?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/hiyenwong-on-the-convergence-and-stability-of-upsidedown-rei)# On the Convergence and Stability of Upside-Down Reinforcement Learning, Goal-Conditioned Supervised Learning, and Online Decision Transformers
**arXiv ID:** 2502.05672
**Authors:** Miroslav Štrupl, Oleg Szehr, Francesco Faccio, Dylan R. Ashley, Rupesh Kumar Srivastava, Jürgen Schmidhuber
**Published:** 2025-02-08T19:26:22Z
**Abstract:**
This article provides a rigorous analysis of convergence and stability of Episodic Upside-Down Reinforcement Learning, Goal-Conditioned Supervised Learning and Online Decision Transformers. These algorithms performed competitively across various benchmarks, from games to robotic tasks, but their theoretical understanding is limited to specific environmental conditions. This work initiates a theoretical foundation for algorithms that build on the broad paradigm of approaching reinforcement learning through supervised learning or sequence modeling. At the core of this investigation lies the analysis of conditions on the underlying environment, under which the algorithms can identify optimal solutions. We also assess whether emerging solutions remain stable in situations where the environment is subject to tiny levels of noise. Specifically, we study the continuity and asymptotic convergence of command-conditioned policies, values and the goal-reaching objective depending on the transition kernel of the underlying Markov Decision Process. We demonstrate that near-optimal behavior is achieved if the transition kernel is located in a sufficiently small neighborhood of a deterministic kernel. The mentioned quantities are continuous (with respect to a specific topology) at deterministic kernels, both asymptotically and after a finite number of learning cycles. The developed methods allow us to present the first explicit estimates on the convergence and stability of policies and values in terms of the underlying transition kernels. On the theoretical side we introduce a number of new concepts to reinforcement learning, like working in segment spaces, studying continuity in quotient topologies and the application of the fixed-point theory of dynamical systems. The theoretical study is accompanied by a detailed investigation of example environments and numerical experiments.
## Skill Description
This skill is generated from the arXiv paper: On the Convergence and Stability of Upside-Down Reinforcement Learning, Goal-Conditioned Supervised Learning, and Online Decision Transformers (2502.05672).
## How to Use
[To be filled in by the user or by future automation]
## References
- [arXiv:2502.05672](http://arxiv.org/abs/2502.05672v2)
Attribution
Related skills
View all in tools →Comments
Loading comments…
Newsletter
Get the weekly list of safe new skills, and the ones we pulled.