Reinforcement Learning Algorithm

Reinforcement learning (RL) algorithms train agents to make optimal decisions by interacting with an environment and maximizing cumulative rewards. Current research emphasizes improving RL's efficiency and stability, focusing on areas like model-based methods incorporating techniques such as Monte Carlo Tree Search, the development of novel algorithms for specific applications (e.g., traffic control, robotics), and addressing challenges in high-dimensional or partially observable environments. The impact of RL spans diverse fields, from optimizing resource allocation in complex systems to developing more effective personalized interventions in healthcare and improving the efficiency of robotic control systems.

Papers

March 11, 2024

$\mathbf{(N,K)}$-Puzzle: A Cost-Efficient Testbed for Benchmarking Reinforcement Learning Algorithms in Generative Language Model
Yufeng Zhang, Liyu Chen, Boyi Liu, Yingxiang Yang, Qiwen Cui, Yunzhe Tao, Hongxia Yang
Language Model Reinforcement Learning Proximal Policy Optimization Reinforcement Learning Algorithm Generative Language Model Reinforcement Learning Benchmark K Content Test Bed Direct Policy

March 5, 2024

A Zero-Shot Reinforcement Learning Strategy for Autonomous Guidewire Navigation
Valentina Scarponi, Michel Duprez, Florent Nageotte, Stéphane Cotin
Zero Shot Reinforcement Learning Algorithm Deep Reinforcement Learning Approach Catheter Path Guidewire Segmentation Endovascular Navigation

March 4, 2024

DACO: Towards Application-Driven and Comprehensive Data Analysis via Code Generation
Xueqing Wu, Rui Zheng, Jingzhen Sha, Te-Lin Wu, Hanyu Zhou, Mohan Tang, Kai-Wei Chang, Nanyun Peng, Haoran Huang
Code Generation MAESTRO Dataset Reinforcement Learning Algorithm Data Annotation

February 26, 2024

February 25, 2024

How Can LLM Guide RL? A Value-Based Approach
Shenao Zhang, Sirui Zheng, Shuqi Ke, Zhihan Liu, Wanxin Jin, Jianbo Yuan, Yingxiang Yang, Hongxia Yang, Zhaoran Wang
Large Language Model Reinforcement Learning Reinforcement Learning Algorithm Value Based Reinforcement Learning Value Based

February 22, 2024

February 14, 2024

How does Your RL Agent Explore? An Optimal Transport Analysis of Occupancy Measure Trajectories
Reabetswe M. Nkhumise, Debabrota Basu, Tony J. Prescott, Aditya Gilra
Reinforcement Learning Optimal Transport Environment Exploration Reinforcement Learning Algorithm Policy Space Uninformed Exploration

February 11, 2024

Using Large Language Models to Automate and Expedite Reinforcement Learning with Reward Machine
Shayan Meshkat Alsadat, Jean-Raphael Gaglione, Daniel Neider, Ufuk Topcu, Zhe Xu
Reinforcement Learning Domain Knowledge Reinforcement Learning Algorithm Closed Loop Decomposed Automation Correction Reward Machine

February 8, 2024

Real-World Fluid Directed Rigid Body Control via Deep Reinforcement Learning
Mohak Bhardwaj, Thomas Lampe, Michael Neunert, Francesco Romano, Abbas Abdolmaleki, Arunkumar Byravan, Markus Wulfmeier, Martin Riedmiller, Jonas Buchli
Reinforcement Learning Deep Reinforcement Learning Reinforcement Learning Algorithm Model Free Reinforcement Learning Fluid Dynamic Deep RL

February 5, 2024

February 1, 2024

Leveraging Approximate Model-based Shielding for Probabilistic Safety Guarantees in Continuous Environments
Alexander W. Goodall, Francesco Belardinelli
Policy Gradient Reinforcement Learning Algorithm Safe Reinforcement Learning Safety Guarantee Continuous Environment Model Based Shielding

January 21, 2024

VQC-Based Reinforcement Learning with Data Re-uploading: Performance and Trainability
Rodrigo Coelho, André Sequeira, Luís Paulo Santos
Reinforcement Learning System Performance Reinforcement Learning Algorithm Variational Quantum Circuit Deep Q Learning Deep Q

January 20, 2024

Detecting Hidden Triggers: Mapping Non-Markov Reward Functions to Markov
Gregory Hyde, Eugene Santos Jr
Reinforcement Learning Algorithm Markov Model Non Markovian Reward Imperceptible Trigger Markovian Reward

December 31, 2023

Tight Finite Time Bounds of Two-Time-Scale Linear Stochastic Approximation with Markovian Noise
Shaan Ul Haque, Sajad Khodadadian, Siva Theja Maguluri
Reinforcement Learning Algorithm Convergence Rate Stochastic Approximation Finite Time

December 14, 2023

Arithmetics-Based Decomposition of Numeral Words -- Arithmetic Conditions give the Unpacking Strategy
Isidor Konrad Maier, Matthias Wolff
Practical Algorithm Reinforcement Learning Algorithm Microbial Decomposition Strategy Discovery Mathematical Understanding Numeral System

December 11, 2023

Reinforcement Learning Algorithm

Papers

$\mathbf{(N,K)}$-Puzzle: A Cost-Efficient Testbed for Benchmarking Reinforcement Learning Algorithms in Generative Language Model

A Zero-Shot Reinforcement Learning Strategy for Autonomous Guidewire Navigation

DACO: Towards Application-Driven and Comprehensive Data Analysis via Code Generation

Reinforcement Learning Based Oscillation Dampening: Scaling up Single-Agent RL algorithms to a 100 AV highway field operational test

Q-FOX Learning: Breaking Tradition in Reinforcement Learning

How Can LLM Guide RL? A Value-Based Approach

Reinforcement Learning with Elastic Time Steps

Model-Based Reinforcement Learning Control of Reaction-Diffusion Problems

How does Your RL Agent Explore? An Optimal Transport Analysis of Occupancy Measure Trajectories

Using Large Language Models to Automate and Expedite Reinforcement Learning with Reward Machine

Real-World Fluid Directed Rigid Body Control via Deep Reinforcement Learning

Assessing the Impact of Distribution Shift on Reinforcement Learning Performance

Open RL Benchmark: Comprehensive Tracked Experiments for Reinforcement Learning

Leveraging Approximate Model-based Shielding for Probabilistic Safety Guarantees in Continuous Environments

VQC-Based Reinforcement Learning with Data Re-uploading: Performance and Trainability

Detecting Hidden Triggers: Mapping Non-Markov Reward Functions to Markov

Tight Finite Time Bounds of Two-Time-Scale Linear Stochastic Approximation with Markovian Noise

Arithmetics-Based Decomposition of Numeral Words -- Arithmetic Conditions give the Unpacking Strategy

Learning Polynomial Representations of Physical Objects with Application to Certifying Correct Packing Configurations

Spreeze: High-Throughput Parallel Reinforcement Learning Framework