Cover Image

TROLL: Trust Regions improve Reinforcement Learning for Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Becker, Philipp, Freymuth, Niklas, Thilges, Serge, Otto, Fabian, Neumann, Gerhard
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

KalMamba: Towards Efficient Probabilistic State Space Models for RL under Uncertainty
by: Becker, Philipp, et al.
Published: (2024)

Open the Black Box: Step-based Policy Updates for Temporally-Correlated Episodic Reinforcement Learning
by: Li, Ge, et al.
Published: (2024)

MaNGO - Adaptable Graph Network Simulators via Meta-Learning
by: Dahlinger, Philipp, et al.
Published: (2025)

Adaptive Swarm Mesh Refinement using Deep Reinforcement Learning with Local Rewards
by: Freymuth, Niklas, et al.
Published: (2024)

Can Neural Networks Provide Latent Embeddings for Telemetry-Aware Greedy Routing?
by: Boltres, Andreas, et al.
Published: (2026)

Efficient Off-Policy Learning for High-Dimensional Action Spaces
by: Otto, Fabian, et al.
Published: (2024)

Combining Reconstruction and Contrastive Methods for Multimodal Representations in RL
by: Becker, Philipp, et al.
Published: (2023)

Improving Long-Range Interactions in Graph Neural Simulators via Hamiltonian Dynamics
by: Hoang, Tai, et al.
Published: (2025)

Diffusion-Based Hierarchical Graph Neural Networks for Simulating Nonlinear Solid Mechanics
by: Würth, Tobias, et al.
Published: (2025)

Iterative Sizing Field Prediction for Adaptive Mesh Generation From Expert Demonstrations
by: Freymuth, Niklas, et al.
Published: (2024)

Context-aware Learned Mesh-based Simulation via Trajectory-Level Meta-Learning
by: Dahlinger, Philipp, et al.
Published: (2025)

Learning Sub-Second Routing Optimization in Computer Networks requires Packet-Level Dynamics
by: Boltres, Andreas, et al.
Published: (2024)

Towards Near-Real-Time Telemetry-Aware Routing with Neural Routing Algorithms
by: Boltres, Andreas, et al.
Published: (2026)

PointPatchRL -- Masked Reconstruction Improves Reinforcement Learning on Point Clouds
by: Gyenes, Balázs, et al.
Published: (2024)

Physics-informed MeshGraphNets (PI-MGNs): Neural finite element solvers for non-stationary and nonlinear simulations on arbitrary meshes
by: Würth, Tobias, et al.
Published: (2024)

Point Cloud Sequence Encoding for Material-conditioned Graph Network Simulators
by: Dahlinger, Philipp, et al.
Published: (2026)

Movement Primitive Diffusion: Learning Gentle Robotic Manipulation of Deformable Objects
by: Scheikl, Paul Maria, et al.
Published: (2023)

AMBER: Adaptive Mesh Generation by Iterative Mesh Resolution Prediction
by: Freymuth, Niklas, et al.
Published: (2025)

Adaptive World Models: Learning Behaviors by Latent Imagination Under Non-Stationarity
by: Gospodinov, Emiliyan, et al.
Published: (2024)

Trust Region-Based Bayesian Optimisation to Discover Diverse Solutions
by: Perera, Kokila Kasuni, et al.
Published: (2025)

Trust Region Constrained Measure Transport in Path Space for Stochastic Optimal Control and Inference
by: Blessing, Denis, et al.
Published: (2025)

Acquiring Diverse Skills using Curriculum Reinforcement Learning with Mixture of Experts
by: Celik, Onur, et al.
Published: (2024)

Integrating Human Knowledge Through Action Masking in Reinforcement Learning for Operations Research
by: Stappert, Mirko, et al.
Published: (2025)

Feasibility-Driven Trust Region Bayesian Optimization
by: Ascia, Paolo, et al.
Published: (2025)

Geometry-aware RL for Manipulation of Varying Shapes and Deformable Objects
by: Hoang, Tai, et al.
Published: (2025)

Diffusion Policies creating a Trust Region for Offline Reinforcement Learning
by: Chen, Tianyu, et al.
Published: (2024)

Rethinking Ratio-Based Trust Regions for Policy Optimization in Multi-Agent Reinforcement Learning
by: Wijesundara, Chulabhaya, et al.
Published: (2026)

Trust-Region Noise Search for Black-Box Alignment of Diffusion and Flow Models
by: Schweiger, Niklas, et al.
Published: (2026)

Trust Region Masking for Long-Horizon LLM Reinforcement Learning
by: Li, Yingru, et al.
Published: (2025)

Large Vision-Language Models for Knowledge-Grounded Data Annotation of Memes
by: Deng, Shiling, et al.
Published: (2025)

Efficient Reinforcement Learning with Large Language Model Priors
by: Yan, Xue, et al.
Published: (2024)

Teaching Large Language Models to Reason with Reinforcement Learning
by: Havrilla, Alex, et al.
Published: (2024)

MuTT: A Multimodal Trajectory Transformer for Robot Skills
by: Kienle, Claudius, et al.
Published: (2024)

TOP-ERL: Transformer-based Off-Policy Episodic Reinforcement Learning
by: Li, Ge, et al.
Published: (2024)

Is In-Context Learning in Large Language Models Bayesian? A Martingale Perspective
by: Falck, Fabian, et al.
Published: (2024)

DIME:Diffusion-Based Maximum Entropy Reinforcement Learning
by: Celik, Onur, et al.
Published: (2025)

SEAR: Sample Efficient Action Chunking Reinforcement Learning
by: Nagy, C. F. Maximilian, et al.
Published: (2026)

Reinforced Model Predictive Control via Trust-Region Quasi-Newton Policy Optimization
by: Brandner, Dean, et al.
Published: (2024)

Reinforcement Learning Finetunes Small Subnetworks in Large Language Models
by: Mukherjee, Sagnik, et al.
Published: (2025)

Trust Region Continual Learning as an Implicit Meta-Learner
by: Wang, Zekun, et al.
Published: (2026)