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

October 14, 2024

DR-MPC: Deep Residual Model Predictive Control for Real-world Social Navigation
James R. Han, Hugues Thomas, Jian Zhang, Nicholas Rhinehart, Timothy D. Barfoot
Reinforcement Learning Deep Reinforcement Learning Model Predictive Control Local Navigation Residual Reinforcement Learning
Burning RED: Unlocking Subtask-Driven Reinforcement Learning and Risk-Awareness in Average-Reward Markov Decision Processes
Juan Sebastian Rojas, Chi-Guhn Lee
Reinforcement Learning Sequential Decision Unlocking Insight Average Reward Markov Decision Process Risk Awareness
Compositional Shielding and Reinforcement Learning for Multi-Agent Systems
Asger Horn Brorholt, Kim Guldstrand Larsen, Christian Schilling
Reinforcement Learning Deep Reinforcement Learning System Description Model Based Shielding High Performing Policy
Reinforcement Learning For Quadrupedal Locomotion: Current Advancements And Future Perspectives
Maurya Gurram, Prakash Kumar Uttam, Shantipal S. Ohol
Reinforcement Learning Recent Advance Quadrupedal Robot Quadrupedal Locomotion Future Perspective
QE-EBM: Using Quality Estimators as Energy Loss for Machine Translation
Gahyun Yoo, Jay Yoon Lee
Language Model Reinforcement Learning Machine Translation NMT Model Quality Estimator
Large Language Model-Enhanced Reinforcement Learning for Generic Bus Holding Control Strategies
Jiajie Yu, Yuhong Wang, Wei Ma
Reinforcement Learning Large Language Adaptive Cruise Control Generic Plugin
Stable Hadamard Memory: Revitalizing Memory-Augmented Agents for Reinforcement Learning
Hung Le, Kien Do, Dung Nguyen, Sunil Gupta, Svetha Venkatesh
Reinforcement Learning Memory Trace Memory Network Memory Model Memory Less Agent
Content Caching-Assisted Vehicular Edge Computing Using Multi-Agent Graph Attention Reinforcement Learning
Jinjin Shen, Yan Lin, Yijin Zhang, Weibin Zhang, Feng Shu, Jun Li
Reinforcement Learning Multi Agent Edge Computing Graph Convolutional Network Network Topology Vehicular Edge Computing

October 13, 2024

Improving Generalization on the ProcGen Benchmark with Simple Architectural Changes and Scale
Andrew Jesson, Yiding Jiang
Reinforcement Learning Deep Reinforcement Learning Strong Generalization 2 Dimensional Visual Analogue Scale 3D Convolutional Enhancing Generalization
Meta-Reinforcement Learning with Universal Policy Adaptation: Provable Near-Optimality under All-task Optimum Comparator
Siyuan Xu, Minghui Zhu
Reinforcement Learning Meta Reinforcement Learning Near Optimality Policy Adaptation Policy Network
Transformers as Game Players: Provable In-context Game-playing Capabilities of Pre-trained Models
Chengshuai Shi, Kun Yang, Jing Yang, Cong Shen
Reinforcement Learning Transformer Megatron Decepticons Full Model Context Learning Multi Agent Capability Evolution Game Playing Agent
Generalization of Compositional Tasks with Logical Specification via Implicit Planning
Duo Xu, Faramarz Fekri
Reinforcement Learning Strong Generalization Goal Conditioned Policy Compositional Task Policy Generalization

October 12, 2024

ActSafe: Active Exploration with Safety Constraints for Reinforcement Learning
Yarden As, Bhavya Sukhija, Lenart Treven, Carmelo Sferrazza, Stelian Coros, Andreas Krause
Reinforcement Learning LeArning Abstract Efficient Exploration Safety Constraint Positive Reinforcement Active Exploration Safe Exploration
Reinforcement Learning in Hyperbolic Spaces: Models and Experiments
Vladimir Jaćimović, Zinaid Kapić, Aladin Crnkić
Reinforcement Learning Full Model Action Space Optical Experiment Black Box Optimization Unknown Environment Hyperbolic Space Dynamical Model
Multiple Ships Cooperative Navigation and Collision Avoidance using Multi-agent Reinforcement Learning with Communication
Y. Wang, Y. Zhao
Reinforcement Learning Multi Agent Reinforcement Learning Multi Agent System Collision Avoidance Timely Communication Unmanned Surface Agent Communication Cooperative Navigation
Towards a Domain-Specific Modelling Environment for Reinforcement Learning
Natalie Sinani, Sahil Salma, Paul Boutot, Sadaf Mustafiz
Reinforcement Learning LeArning Abstract Positive Reinforcement Domain Specific Model Model Driven Modeling Language
SeRA: Self-Reviewing and Alignment of Large Language Models using Implicit Reward Margins
Jongwoo Ko, Saket Dingliwal, Bhavana Ganesh, Sailik Sengupta, Sravan Bodapati, Aram Galstyan
Reinforcement Learning Alignment Problem Direct Preference Optimization Self Feedback Self Alignment Implicit Reward Alignment Algorithm

October 11, 2024

Enhancing Multi-Step Reasoning Abilities of Language Models through Direct Q-Function Optimization
Guanlin Liu, Kaixuan Ji, Renjie Zheng, Zheng Wu, Chen Dun, Quanquan Gu, Lin Yan
Language Model Reinforcement Learning Step by Step Reasoning Q Function
Physical Simulation for Multi-agent Multi-machine Tending
Abdalwhab Abdalwhab, Giovanni Beltrame, David St-Onge
Reinforcement Learning Non Humanoid Robot Robotics Domain Physical Simulation Multi Agent Environment Large Scale Robotic
Hierarchical Universal Value Function Approximators
Rushiv Arora
Reinforcement Learning Value Function Hierarchical Reinforcement Learning

Reinforcement Learning

Papers

DR-MPC: Deep Residual Model Predictive Control for Real-world Social Navigation

Burning RED: Unlocking Subtask-Driven Reinforcement Learning and Risk-Awareness in Average-Reward Markov Decision Processes

Compositional Shielding and Reinforcement Learning for Multi-Agent Systems

Reinforcement Learning For Quadrupedal Locomotion: Current Advancements And Future Perspectives

QE-EBM: Using Quality Estimators as Energy Loss for Machine Translation

Large Language Model-Enhanced Reinforcement Learning for Generic Bus Holding Control Strategies

Stable Hadamard Memory: Revitalizing Memory-Augmented Agents for Reinforcement Learning

Content Caching-Assisted Vehicular Edge Computing Using Multi-Agent Graph Attention Reinforcement Learning

Improving Generalization on the ProcGen Benchmark with Simple Architectural Changes and Scale

Meta-Reinforcement Learning with Universal Policy Adaptation: Provable Near-Optimality under All-task Optimum Comparator

Transformers as Game Players: Provable In-context Game-playing Capabilities of Pre-trained Models

Generalization of Compositional Tasks with Logical Specification via Implicit Planning

ActSafe: Active Exploration with Safety Constraints for Reinforcement Learning

Reinforcement Learning in Hyperbolic Spaces: Models and Experiments

Multiple Ships Cooperative Navigation and Collision Avoidance using Multi-agent Reinforcement Learning with Communication

Towards a Domain-Specific Modelling Environment for Reinforcement Learning

SeRA: Self-Reviewing and Alignment of Large Language Models using Implicit Reward Margins

Enhancing Multi-Step Reasoning Abilities of Language Models through Direct Q-Function Optimization

Physical Simulation for Multi-agent Multi-machine Tending

Hierarchical Universal Value Function Approximators