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

November 17, 2024

Reinforcing Competitive Multi-Agents for Playing So Long Sucker
Medant Sharan, Chandranath Adak
Reinforcement Learning Multi Agent DQN Agent Game Diplomacy
Modulating Reservoir Dynamics via Reinforcement Learning for Efficient Robot Skill Synthesis
Zahra Koulaeizadeh, Erhan Oztop
Reinforcement Learning High Efficiency Reservoir Computing Skill Learning Stochastic Dynamical System Reservoir Dynamic Random Neural Network

November 16, 2024

BPO: Towards Balanced Preference Optimization between Knowledge Breadth and Depth in Alignment
Sizhe Wang, Yongqi Tong, Hengyuan Zhang, Dawei Li, Xin Zhang, Tianlong Chen
Large Language Model Reinforcement Learning Alignment Problem Large Depth Preference Optimization Depth Information Alignment Tuning
Stable Continual Reinforcement Learning via Diffusion-based Trajectory Replay
Feng Chen, Fuguang Han, Cong Guan, Lei Yuan, Zhilong Zhang, Yang Yu, Zongzhang Zhang
Reinforcement Learning Continual Reinforcement Learning RePLAy Loss Trajectory Replay
Wireless Resource Allocation with Collaborative Distributed and Centralized DRL under Control Channel Attacks
Ke Wang, Wanchun Liu, Teng Joon Lim
Reinforcement Learning Resource Allocation Cyber Physical System DRL Algorithm

November 15, 2024

Guiding Reinforcement Learning Using Uncertainty-Aware Large Language Models
Maryam Shoaeinaeini, Brent Harrison
Reinforcement Learning Full Model Robust Reinforcement Learning Fine Tuned LLM Overconfidence Problem
Multi-agent Path Finding for Timed Tasks using Evolutionary Games
Sheryl Paul, Anand Balakrishnan, Xin Qin, Jyotirmoy V. Deshmukh
Reinforcement Learning Multi Agent Path Finding State of the Art Reinforcement Evolutionary Game Agent Team MULTI Agent
Towards Sample-Efficiency and Generalization of Transfer and Inverse Reinforcement Learning: A Comprehensive Literature Review
Hossein Hassani, Roozbeh Razavi-Far, Mehrdad Saif, Liang Lin
Reinforcement Learning Strong Generalization Reward Function Formality Transfer Inverse Reinforcement Learning Sample Efficiency Sequential Decision Making Problem Inverse Task
The Surprising Ineffectiveness of Pre-Trained Visual Representations for Model-Based Reinforcement Learning
Moritz Schneider, Robert Krug, Narunas Vaskevicius, Luigi Palmieri, Joschka Boedecker
Reinforcement Learning Model Free Reinforcement Learning Pre Trained Representation Visual Reinforcement Learning Surprising Effectiveness
Guided Learning: Lubricating End-to-End Modeling for Multi-stage Decision-making
Jian Guo, Saizhuo Wang, Yiyan Qi
Reinforcement Learning Decision Making Multi Stage End to End Model Quantitative Investment
Statistical Analysis of Policy Space Compression Problem
Majid Molaei, Marcello Restelli, Alberto Maria Metelli, Matteo Papini
Reinforcement Learning Statistical Analysis Policy Space Policy Distribution

November 14, 2024

Edge Caching Optimization with PPO and Transfer Learning for Dynamic Environments
Farnaz Niknia, Ping Wang
Reinforcement Learning Transfer Learning Proximal Policy Optimization Environment Feature Policy Optimization Edge Caching Backhaul Network
To bootstrap or to rollout? An optimal and adaptive interpolation
Wenlong Mou, Jian Qian
Reinforcement Learning Bellman Operator Sample Efficient Adaptation Bellman Update
Developement of Reinforcement Learning based Optimisation Method for Side-Sill Design
Aditya Borse, Rutwik Gulakala, Marcus Stoffel
Reinforcement Learning Development Activity Optimal Design Crash Data Sideslip Angle
Iterative Batch Reinforcement Learning via Safe Diversified Model-based Policy Search
Amna Najib, Stefan Depeweg, Phillip Swazinna
Reinforcement Learning Offline Reinforcement Learning Policy Learning Batch Reinforcement Learning Policy Search Model Based Policy

November 13, 2024

Code-mixed LLM: Improve Large Language Models' Capability to Handle Code-Mixing through Reinforcement Learning from AI Feedback
Wenbo Zhang, Aditya Majumdar, Amulya Yadav
Large Language Model Reinforcement Learning Code Mixed Code Switched Code LLM AI Feedback Code Mixing
Liner Shipping Network Design with Reinforcement Learning
Utsav Dutta, Yifan Lin, Zhaoyang Larry Jin
Reinforcement Learning Multi Commodity Flow Maritime Industry Transit Network Design
Recommender systems and reinforcement learning for human-building interaction and context-aware support: A text mining-driven review of scientific literature
Wenhao Zhang, Matias Quintana, Clayton Miller
Reinforcement Learning Recommender System Narrative Review External Control Recommendation System Indoor Environment Occupant Persona
Estimating unknown parameters in differential equations with a reinforcement learning based PSO method
Wenkui Sun, Xiaoya Fan, Lijuan Jia, Tinyi Chu, Shing-Tung Yau, Rongling Wu, Zhong Wang
Reinforcement Learning Differential Equation Particle Swarm Optimization Particle Swarm Traditional Optimization Unknown Parameter
Robot See, Robot Do: Imitation Reward for Noisy Financial Environments
Sven Goluža, Tomislav Kovačević, Stjepan Begušić, Zvonko Kostanjčar
Reinforcement Learning Robot Person Imitation Learning Positive Reinforcement Reward Function Design Robust Reward Robot Gaze Conditioned Imitation

Reinforcement Learning

Papers

Reinforcing Competitive Multi-Agents for Playing So Long Sucker

Modulating Reservoir Dynamics via Reinforcement Learning for Efficient Robot Skill Synthesis

BPO: Towards Balanced Preference Optimization between Knowledge Breadth and Depth in Alignment

Stable Continual Reinforcement Learning via Diffusion-based Trajectory Replay

Wireless Resource Allocation with Collaborative Distributed and Centralized DRL under Control Channel Attacks

Guiding Reinforcement Learning Using Uncertainty-Aware Large Language Models

Multi-agent Path Finding for Timed Tasks using Evolutionary Games

Towards Sample-Efficiency and Generalization of Transfer and Inverse Reinforcement Learning: A Comprehensive Literature Review

The Surprising Ineffectiveness of Pre-Trained Visual Representations for Model-Based Reinforcement Learning

Guided Learning: Lubricating End-to-End Modeling for Multi-stage Decision-making

Statistical Analysis of Policy Space Compression Problem

Edge Caching Optimization with PPO and Transfer Learning for Dynamic Environments

To bootstrap or to rollout? An optimal and adaptive interpolation

Developement of Reinforcement Learning based Optimisation Method for Side-Sill Design

Iterative Batch Reinforcement Learning via Safe Diversified Model-based Policy Search

Code-mixed LLM: Improve Large Language Models' Capability to Handle Code-Mixing through Reinforcement Learning from AI Feedback

Liner Shipping Network Design with Reinforcement Learning

Recommender systems and reinforcement learning for human-building interaction and context-aware support: A text mining-driven review of scientific literature

Estimating unknown parameters in differential equations with a reinforcement learning based PSO method

Robot See, Robot Do: Imitation Reward for Noisy Financial Environments