Reinforcement Learning

Reinforcement learning (RL) focuses on training agents to make optimal decisions in an environment by learning through trial and error, aiming to maximize cumulative rewards. Current research emphasizes improving RL's efficiency and robustness, particularly in areas like human-in-the-loop training (e.g., using human feedback to refine models), handling uncertainty and sparse rewards, and scaling to complex tasks (e.g., robotics, autonomous driving). Prominent approaches involve various policy gradient methods, Monte Carlo Tree Search, and the integration of large language models for improved decision-making and task decomposition. These advancements are driving progress in diverse fields, including robotics, game playing, and the development of more human-aligned AI systems.

Papers

December 12, 2024

In-Dataset Trajectory Return Regularization for Offline Preference-based Reinforcement Learning
Songjun Tu, Jingbo Sun, Qichao Zhang, Yaocheng Zhang, Jia Liu, Ke Chen, Dongbin Zhao
Reinforcement Learning Reward Model Action Free Offline Preference Based Reinforcement Learning Trajectory Regularization Continual Offline Reinforcement Learning
PickLLM: Context-Aware RL-Assisted Large Language Model Routing
Dimitrios Sikeridis, Dennis Ramdass, Pranay Pareek
Reinforcement Learning Inference Latency
Efficient Reinforcement Learning for Optimal Control with Natural Images
Peter N. Loxley
Reinforcement Learning Optimal Policy Optimal Control Natural Image Sequential Decision Efficient Reinforcement Learning

December 10, 2024

Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline Data
Zhiyuan Zhou, Andy Peng, Qiyang Li, Sergey Levine, Aviral Kumar
Reinforcement Learning Fine Tuning Offline Data Online Fine Tuning
Optimizing Sensor Redundancy in Sequential Decision-Making Problems
Jonas Nüßlein, Maximilian Zorn, Fabian Ritz, Jonas Stein, Gerhard Stenzel, Julian Schönberger, Thomas Gabor, Claudia Linnhoff-Popien
Reinforcement Learning Optimization Purpose Sequential Decision Making Problem Reinforcement Learning Policy Robot Environment Quadratic Program
Swarm Behavior Cloning
Jonas Nüßlein, Maximilian Zorn, Philipp Altmann, Claudia Linnhoff-Popien
Reinforcement Learning Imitation Learning Behavior Cloning State Action Pair
ConfigX: Modular Configuration for Evolutionary Algorithms via Multitask Reinforcement Learning
Hongshu Guo, Zeyuan Ma, Jiacheng Chen, Yining Ma, Zhiguang Cao, Xinglin Zhang, Yue-Jiao Gong
Reinforcement Learning Multi Task Meta Learning Evolutionary Algorithm System Configuration
Progressive-Resolution Policy Distillation: Leveraging Coarse-Resolution Simulation for Time-Efficient Fine-Resolution Policy Learning
Yuki Kadokawa, Hirotaka Tahara, Takamitsu Matsubara
Reinforcement Learning Simulation Study Real World Environment Policy Distillation Coarse Resolution
Effective Reward Specification in Deep Reinforcement Learning
Julien Roy
Reinforcement Learning Deep Reinforcement Learning Sequential Decision Making Problem
Reinforcement Learning Policy as Macro Regulator Rather than Macro Placer
Ke Xue, Ruo-Tong Chen, Xi Lin, Yunqi Shi, Shixiong Kai, Siyuan Xu, Chao Qian
Reinforcement Learning Chip Design Global Scale
Personalized and Sequential Text-to-Image Generation
Ofir Nabati, Guy Tennenholtz, ChihWei Hsu, Moonkyung Ryu, Deepak Ramachandran, Yinlam Chow, Xiang Li, Craig Boutilier
Reinforcement Learning Text to Image Generation Text to Image Model Personalized Subject User Interaction

December 9, 2024

Unraveling the Complexity of Memory in RL Agents: an Approach for Classification and Evaluation
Egor Cherepanov, Nikita Kachaev, Artem Zholus, Alexey K. Kovalev, Aleksandr I. Panov
Reinforcement Learning Classification Code Global Evaluation Complexity Matter Memory Trace Reinforcement Learning Agent Memory Less Agent
Skill-Enhanced Reinforcement Learning Acceleration from Demonstrations
Hanping Zhang, Yuhong Guo
Reinforcement Learning Noisy Demonstration Downstream Policy Learning

December 8, 2024

Does RLHF Scale? Exploring the Impacts From Data, Model, and Method
Zhenyu Hou, Pengfan Du, Yilin Niu, Zhengxiao Du, Aohan Zeng, Xiao Liu, Minlie Huang, Hongning Wang, Jie Tang, Yuxiao Dong
Reinforcement Learning Full Model Raw Data Practical Method Reward Model Impact Assessment RLHF V
Mean--Variance Portfolio Selection by Continuous-Time Reinforcement Learning: Algorithms, Regret Analysis, and Empirical Study
Yilie Huang, Yanwei Jia, Xun Yu Zhou
Reinforcement Learning LeArning Abstract Practical Algorithm Regret Analysis Portfolio Selection Variance Portfolio Black Scholes
Reinforcement Learning for a Discrete-Time Linear-Quadratic Control Problem with an Application
Lucky Li
Reinforcement Learning Application Proficiency Optimal Control Discrete Time Right Problem Linear Quadratic Regulator Control Algorithm
Strategizing Equitable Transit Evacuations: A Data-Driven Reinforcement Learning Approach
Fang Tang, Han Wang, Maria Laura Delle Monache
Reinforcement Learning Markov Decision Process Data Driven Hurricane Evacuation Learning Approach Evacuation Decision

Reinforcement Learning

Papers

In-Dataset Trajectory Return Regularization for Offline Preference-based Reinforcement Learning

PickLLM: Context-Aware RL-Assisted Large Language Model Routing

Efficient Reinforcement Learning for Optimal Control with Natural Images

Learning Sketch Decompositions in Planning via Deep Reinforcement Learning

Subspace-wise Hybrid RL for Articulated Object Manipulation

SINERGYM -- A virtual testbed for building energy optimization with Reinforcement Learning

Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline Data

Optimizing Sensor Redundancy in Sequential Decision-Making Problems

Swarm Behavior Cloning

ConfigX: Modular Configuration for Evolutionary Algorithms via Multitask Reinforcement Learning

Progressive-Resolution Policy Distillation: Leveraging Coarse-Resolution Simulation for Time-Efficient Fine-Resolution Policy Learning

Effective Reward Specification in Deep Reinforcement Learning

Reinforcement Learning Policy as Macro Regulator Rather than Macro Placer

Personalized and Sequential Text-to-Image Generation

Unraveling the Complexity of Memory in RL Agents: an Approach for Classification and Evaluation

Skill-Enhanced Reinforcement Learning Acceleration from Demonstrations

Does RLHF Scale? Exploring the Impacts From Data, Model, and Method

Mean--Variance Portfolio Selection by Continuous-Time Reinforcement Learning: Algorithms, Regret Analysis, and Empirical Study

Reinforcement Learning for a Discrete-Time Linear-Quadratic Control Problem with an Application

Strategizing Equitable Transit Evacuations: A Data-Driven Reinforcement Learning Approach