Cover Image

Stealing That Free Lunch: Exposing the Limits of Dyna-Style Reinforcement Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Barkley, Brett, Fridovich-Keil, David
Format:	Preprint
Published:	2024
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

A Forensic Analysis of Synthetic Data in RL: Diagnosing and Solving Algorithmic Failures in Model-Based Policy Optimization
by: Barkley, Brett, et al.
Published: (2025)

Scaling Pretrained Representations Enables Label-Free Out-of-Distribution Detection Without Fine-Tuning
by: Barkley, Brett, et al.
Published: (2026)

SCOPED: Score-Curvature Out-of-distribution Proximity Evaluator for Diffusion
by: Barkley, Brett, et al.
Published: (2025)

Decomposing Control Lyapunov Functions for Efficient Reinforcement Learning
by: Lopez, Antonio, et al.
Published: (2024)

Learning to Walk from Three Minutes of Real-World Data with Semi-structured Dynamics Models
by: Levy, Jacob, et al.
Published: (2024)

Dyna-Style Safety Augmented Reinforcement Learning: Staying Safe in the Face of Uncertainty
by: Eisele, Artur, et al.
Published: (2026)

A Recovery Guarantee for Sparse Neural Networks
by: Fridovich-Keil, Sara, et al.
Published: (2025)

Dyna-Style Reinforcement Learning Modeling and Control of Non-linear Dynamics
by: Abdelsalam, Karim, et al.
Published: (2025)

Learning responsibility allocations for multi-agent interactions: A differentiable optimization approach with control barrier functions
by: Remy, Isaac, et al.
Published: (2024)

No Free Lunch: Fundamental Limits of Learning Non-Hallucinating Generative Models
by: Wu, Changlong, et al.
Published: (2024)

Physics-Informed Model and Hybrid Planning for Efficient Dyna-Style Reinforcement Learning
by: Asri, Zakariae El, et al.
Published: (2024)

Monotonic Transformation Invariant Multi-task Learning
by: Murthy, Surya, et al.
Published: (2025)

When to Trust Your Data: Enhancing Dyna-Style Model-Based Reinforcement Learning With Data Filter
by: Li, Yansong, et al.
Published: (2024)

KLIP: localized distribution shift detection via KL-divergence with diffusion priors in Inverse Problems
by: Kheirandish, Alireza, et al.
Published: (2026)

Celo2: Towards Learned Optimization Free Lunch
by: Moudgil, Abhinav, et al.
Published: (2026)

Neural Operators for Multi-Task Control and Adaptation
by: Sewell, David, et al.
Published: (2026)

Dyna-Style Learning with A Macroscopic Model for Vehicle Platooning in Mixed-Autonomy Traffic
by: Zou, Yichuan, et al.
Published: (2024)

InfoNCE is a Free Lunch for Semantically guided Graph Contrastive Learning
by: Wang, Zixu, et al.
Published: (2025)

The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning
by: Goldblum, Micah, et al.
Published: (2023)

Symbolic Regression on Sparse and Noisy Data with Gaussian Processes
by: Hsin, Junette, et al.
Published: (2023)

Generalized Information Gathering Under Dynamics Uncertainty
by: Palafox, Fernando, et al.
Published: (2026)

No Free Lunch: Non-Asymptotic Analysis of Prediction-Powered Inference
by: Mani, Pranav, et al.
Published: (2025)

A Framework for Finding Local Saddle Points in Two-Player Zero-Sum Black-Box Games
by: Agarwal, Shubhankar, et al.
Published: (2025)

Controllability in preference-conditioned multi-objective reinforcement learning
by: Molins, Pau de las Heras, et al.
Published: (2026)

A Flow Matching Algorithm for Many-Shot Adaptation to Unseen Distributions
by: Ingebrand, Tyler, et al.
Published: (2026)

No Free Lunch: Rethinking Internal Feedback for LLM Reasoning
by: Zhang, Yanzhi, et al.
Published: (2025)

Active Inverse Learning in Stackelberg Trajectory Games
by: Ward, William, et al.
Published: (2023)

Integrating Lagrangian Neural Networks into the Dyna Framework for Reinforcement Learning
by: Das, Shreya, et al.
Published: (2026)

Free Lunch for Stabilizing Rectified Flow Inversion
by: Wang, Chenru, et al.
Published: (2026)

Meta-Learning Online Dynamics Model Adaptation in Off-Road Autonomous Driving
by: Levy, Jacob, et al.
Published: (2025)

Bayesian Inverse Games with High-Dimensional Multi-Modal Observations
by: Jain, Yash, et al.
Published: (2026)

StyleShield: Exposing the Fragility of AIGC Detectors through Continuous Controllable Style Transfer
by: Zheng, Guantian
Published: (2026)

DynaMITE-RL: A Dynamic Model for Improved Temporal Meta-Reinforcement Learning
by: Liang, Anthony, et al.
Published: (2024)

Predictive Safety Shield for Dyna-Q Reinforcement Learning
by: Pin, Jin, et al.
Published: (2025)

No-Free-Lunch Theories for Tensor-Network Machine Learning Models
by: Wu, Jing-Chuan, et al.
Published: (2024)

FLOSS: Free Lunch in Open-vocabulary Semantic Segmentation
by: Benigmim, Yasser, et al.
Published: (2025)

Data-Driven Modeling and Correction of Vehicle Dynamics
by: Ly, Nguyen, et al.
Published: (2025)

Free Lunch in the Forest: Functionally-Identical Pruning of Boosted Tree Ensembles
by: Emine, Youssouf, et al.
Published: (2024)

A Free Lunch in LLM Compression: Revisiting Retraining after Pruning
by: Wagner, Moritz, et al.
Published: (2025)

A No Free Lunch Theorem for Human-AI Collaboration
by: Peng, Kenny, et al.
Published: (2024)