2026· KR Doctoral Consortium· pp. 36-43· 0 citations· 18 references
Computer Science
TL;DR
The central research goal is to develop a framework for reliable long-horizon generalization in reinforcement learning from temporal-logic specifications, and the key idea is to use logical specifications not only to describe complex tasks, but also to define structured families of related tasks in which generalization can be formalized, learned, and eventually verified.
This dissertation presents a work in safe RL, where agents must also respect safety constraints using pure-past linear-time temporal logic (PPLTL), and presents how to enforce safety constraints using pure-past linear-time temporal logic (PPLTL).
The Safe Deep Successor Representation is proposed, a novel method that allows quick retraining of policies towards new cost structures and is competitive on a simple navigation task while being considerably more flexible.
Michaela Girstl, Alexander Mattick, Christopher Mutschler· Trans. Mach. Learn. Res.· 0 citations
River, a simple training recipe that improves reward quality by filtering low-quality environments and augmenting outcome rewards with process-level behavior regularization is proposed, which achieves the best performance among evaluated open-source RL-trained 8B models across four terminal-agent benchmarks.
Yi-Fan Yao, Bo Pang, Xuan-Phi Nguyen et al.· 2 citations
Desc descriptive evidence is provided that long-horizon multi-tool post-training can change ways of working that transfer beyond its training domain, and both software-engineering benchmarks improve despite the training collection containing no software-engineering tasks.
Sushant Mehta, Logan Ritchie, Liudas Panavas et al.· 0 citations
This work introduces a surprisingly simple neural network architecture change: a learnable, state-independent attention mask applied to the inputs of the policy and value networks and trained end-to-end using only the RL objective.
LA-MAML (Language Adapted MAML), which modifies the inner loop by adapting the global policy parameters in a single step through a learned embedding of the task instruction, replacing the inner loop trajectory collection and gradient-based updates.
Garvit Singla, U. M. Natarajan, Raghuram Bharadwaj Diddigi· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
