New #TMLR-Paper-with-Video:

A Survey of Flow Matching in Reinforcement Learning

Nabuat Zaman Nahim, Fairoz Nower Khan, Peizhong Ju

https://tmlr.infinite-conf.org/paper_pages/P6e5IC4gPe

#flow #reinforcement #learning

Attention Trajectories as a Diagnostic Axis for Deep Reinforcement Learning

Charlotte Beylier, Hannah Selder, Arthur Fleig, Simon M. Hofmann, Nico Scherf

Action editor: Dennis Wei

https://openreview.net/forum?id=0aa9zthk7k

#attention #saliency #reinforcement

New #TMLR-Paper-with-Video:

Do Object Channels Improve Robustness in Deep Reinforcement Learning?

Jannis Blüml, Cedric Derstroff, Bjarne Gregori et al.

https://tmlr.infinite-conf.org/paper_pages/7BFbso4B3R

#pixels #pixel #reinforcement

Supervised, unsupervised, reinforcement and self-supervised learning - what each one needs and the problems it suits.
#ai #machine-learning #reinforcement-learning #self-supervised-learning
https://stdout.adegoodyer.com/posts/types-of-learning/

New #TMLR-Paper-with-Video:

Revisiting Neighbourhoods in Mean Field Reinforcement Learning

Sriram Ganapathi Subramanian, Matthew E. Taylor, Kate Larson, Mark Crowley, Pascal Poupart

https://tmlr.infinite-conf.org/paper_pages/PQ5R7K0WDc

#reinforcement #agents #agent

Objective-Behavior Alignment: Diagnostics for MORL Policy Selection

Antonio Mone, Zuzanna Osika, Florian Felten et al.

Action editor: Li Shen

https://openreview.net/forum?id=hfnMLNCCYz

#reinforcement #objectives #objective

NashPG: A Policy Gradient Method with Iteratively Refined Regularization for Finding Nash Equilibria

Eason Yu, Tzu Hao Liu, Clement Louis Canonne et al.

Action editor: Ahmet Alacaoglu

https://openreview.net/forum?id=yIA2Fjs1FK

#nashpg #regularization #reinforcement

New #J2C Certification:

POPE: Learning to Reason on Hard Problems via Privileged On-Policy Exploration

Yuxiao Qu, Amrith Setlur, Virginia Smith, Ruslan Salakhutdinov, Aviral Kumar

https://openreview.net/forum?id=pbyIoUW7YV

#reinforcement #exploration #challenging

New #TMLR-Paper-with-Video:

Divide and Conquer: Selective Value Learning and Policy Optimization for Offline Safe Reinforcement ...

Jiahui Zhu, Lei Ying, Honghao Wei

https://tmlr.infinite-conf.org/paper_pages/4KYrv6qYMl

#reinforcement #learns #reward

Reinforcement Learning for Symbolic Equation Solving

Kevin O'Keeffe

Action editor: Wei Huang

https://openreview.net/forum?id=JlC5BJiikD

#reinforcement #learns #symbolic

New #TMLR-Paper-with-Video:

Reward Engineering for Spatial Epidemic Simulations: A Reinforcement Learning Platform for Individua...

Radman Rakhshandehroo, Daniel Coombs

https://tmlr.infinite-conf.org/paper_pages/yPEASsx3hk

#reinforcement #reward #epidemic

Don't Forget the Critic: Value-Based Data Rehearsal for Multi-Cyclic Continual Reinforcement Lear...

Benjamin Poole, Andrew Quinn, Li Yang, Minwoo Lee

Action editor: Michele Caprio

https://openreview.net/forum?id=wYayhflqqR

#forgetting #reinforcement #qreg

Offline Meta-Reinforcement Learning in Piecewise Stationary Environments

Mohammadreza Nakhaeinezhad, Aidan Scannell, Joni Pajarinen

Action editor: Dennis Soemers

https://openreview.net/forum?id=gp1mAySr25

#reinforcement #adaptive #exploration

New #TMLR-Paper-with-Video:

Provably Efficient Reward Transfer in Reinforcement Learning with Discrete Markov Decision Processes

Kevin Jatin Vora, Yu Zhang

https://tmlr.infinite-conf.org/paper_pages/u2b31c9Noe

#reinforcement #reward #learning

New #TMLR-Paper-with-Video:

A Multi-Fidelity Control Variate Approach for Policy Gradient Estimation

Xinjie Liu, Cyrus Neary, Kushagra Gupta et al.

https://tmlr.infinite-conf.org/paper_pages/zAo0L7Dcqt

#reinforcement #reinforce #trained

A Hierarchical Geometric Observation Interface for Spatial Planning in Reinforcement Learning

Andres R. Zapata Rodriguez, Hongpeng Cao, Raphael Trumpp, Marco Caccamo

Action editor: William Redman

https://openreview.net/forum?id=U10DFNcMrW

#planning #reinforcement #navigation

Cross-Domain Offline Policy Adaptation via Selective Transition Correction

Mengbei Yan, Jiafei Lyu, Shengjie Sun et al.

Action editor: Wilka Carvalho

https://openreview.net/forum?id=TupiNRpgHw

#reinforcement #adaptation #rewards

"Does this CNOT spark joy? Teaching an RL agent to tidy quantum circuits ✨" by João Galego

#amazon-braket #reinforcement-learning

A new JAX-based benchmark, PowerZooJax, offers GPU-resident reinforcement learning evaluation for five constrained power system tasks, spanning generation through data center microgrids. It rewrites core power operations as…

#cybersecurity #AI #reinforcement #power
https://arxiv.org/abs/2609.36052

ACRL: Adaptive Control of Training-Inference Discrepancy for Stable Reinforcement Learning

Wenwu Fan, Zhijie Xia, Qihong Lin, Zhuo Zheng, Sihao Wang, QiangChen, Liangsheng Zhu

Action editor: Shangtong Zhang

https://openreview.net/forum?id=8sBZSgAkAH

#adaptive #adaptively #reinforcement