Reinforcement Learning 16

Hello!

This is going to be a very short newsletter, just the classification of articles and some articles I found especially interesting.

Articles I found especially interesting:

1. TreeC: a method to generate interpretable energy management systems using a metaheuristic algorithm

2. A Review of Deep Learning for Video Captioning

3. MDDL: A Framework for Reinforcement Learning-based Position Allocation in Multi-Channel Feed

4. Bridging RL Theory and Practice with the Effective Horizon

5. Heterogeneous-Agent Reinforcement Learning

6. A Review of Symbolic, Subsymbolic and Hybrid Methods for Sequential Decision Making

7. Leveraging Deep Reinforcement Learning for Metacognitive Interventions across Intelligent Tutoring Systems

8. Mastering Asymmetrical Multiplayer Game with Multi-Agent Asymmetric-Evolution Reinforcement Learning

9. Boosting Theory-of-Mind Performance in Large Language Models via Prompting

10. Alzheimers Disease Diagnosis using Machine Learning: A Review

11. Model Based Reinforcement Learning for Personalized Heparin Dosing

New papers (17th-24th April)

1. Engineering Applications

   1. Cyber Security

      1. QuMoS: A Framework for Preserving Security of Quantum Machine Learning Model

      2. Training Automated Defense Strategies Using Graph-based Cyber Attack Simulations¡

   2. Energy

      1. On Fast-Converged Reinforcement Learning for Optimal Dispatch of Large-Scale Power Systems under Transient Security Constraints

      2. Safe reinforcement learning with self-improving hard constraints for multi-energy management systems

      3. TreeC: a method to generate interpretable energy management systems using a metaheuristic algorithm INT INT

   3. Image & Video

      1. A Review of Deep Learning for Video Captioning INT

      2. DeePLT: Personalized Lighting Facilitates by Trajectory Prediction of Recognized Residents in the Smart Home

      3. Search-Map-Search: A Frame Selection Paradigm for Action Recognition

   4. Industrial Applications

      1. A study on a Q-Learning algorithm application to a manufacturing assembly problem

      2. Cooperative Multi-Agent Reinforcement Learning for Inventory Management

      3. Integrated Ray-Tracing and Coverage Planning Control using Reinforcement Learning

      4. MDDL: A Framework for Reinforcement Learning-based Position Allocation in Multi-Channel Feed INT

   5. Navigation

      1. AutoVRL: A High Fidelity Autonomous Ground Vehicle Simulator for Sim-to-Real Deep Reinforcement Learning

      2. Autonomous Agent for Beyond Visual Range Air Combat: A Deep Reinforcement Learning Approach

      3. Control and Coordination of a SWARM of Unmanned Surface Vehicles using Deep Reinforcement Learning in ROS

      4. FastRLAP: A System for Learning High-Speed Driving via Deep RL and Autonomous Practicing

      5. Generative AI-enabled Vehicular Networks: Fundamentals, Framework, and Case Study

      6. Integration of Reinforcement Learning Based Behavior Planning With Sampling Based Motion Planning for Automated Driving

      7. Reinforcement Learning Approaches for Traffic Signal Control under Missing Data

   6. Networks

      1. Secured and Cooperative Publish/Subscribe Scheme in Autonomous Vehicular Networks

   7. Robotics

      1. Affordances from Human Videos as a Versatile Representation for Robotics

      2. Benchmarking Actor-Critic Deep Reinforcement Learning Algorithms for Robotics Control with Action Constraints

      3. CASOG: Conservative Actor-critic with SmOoth Gradient for Skill Learning in Robot-Assisted Intervention

      4. Continuous Versatile Jumping Using Learned Action Residuals

      5. Contrastive Language, Action, and State Pre-training for Robot Learning

      6. Learning and Adapting Agile Locomotion Skills by Transferring Experience

      7. Progressive Transfer Learning for Dexterous In-Hand Manipulation with Multi-Fingered Anthropomorphic Hand

      8. Reinforcement Learning for Picking Cluttered General Objects with Dense Object Descriptors

      9. Torque-based Deep Reinforcement Learning for Task-and-Robot Agnostic Learning on Bipedal Robots Using Sim-to-Real Transfer

2. Reinforcement Learning Theory

   1. Actor Critic

      1. Topological Guided Actor-Critic Modular Learning of Continuous Systems with Temporal Objectives

   2. Control Theory

   3. Aiding reinforcement learning for set point control

   4. Evolutionary Learning

      1. Evolving Constrained Reinforcement Learning Policy

      2. Noise-Reuse in Online Evolution Strategies

   5. Exploration Methods

      1. DEIR: Efficient and Robust Exploration through Discriminative-Model-Based Episodic Intrinsic Rewards

   6. Explainable Machine Learning

      1. Deep Explainable Relational Reinforcement Learning: A Neuro-Symbolic Approach

   7. Graph RL

      1. Graph Exploration for Effective Multi-agent Q-Learning

   8. Hierarchical RL

      1. H-TSP: Hierarchically Solving the Large-Scale Travelling Salesman Problem

   9. Imitation / Inverse / Demonstration Reinforcement Learning

      1. Finite-Sample Bounds for Adaptive Inverse Reinforcement Learning using Passive Langevin Dynamics

      2. Learning Representative Trajectories of Dynamical Systems via Domain-Adaptive Imitation

      3. Observer-Feedback-Feedforward Controller Structures in Reinforcement Learning

      4. OptoGPT: A Foundation Model for Inverse Design in Optical Multilayer Thin Film Structures

   10. Markov Decision Processes / Deep Theory

       1. Bridging RL Theory and Practice with the Effective Horizon INT

       2. End-to-End Policy Gradient Method for POMDPs and Explainable Agents

       3. Inducing Stackelberg Equilibrium through Spatio-Temporal Sequential Decision-Making in Multi-Agent Reinforcement Learning

   11. Memory optimization

       1. Two-Memory Reinforcement Learning

   12. Multi-Agent RL

       1. Heterogeneous-Agent Reinforcement Learning INT

       2. Interpretability for Conditional Coordinated Behavior in Multi-Agent Reinforcement Learning

   13. Model-free

       1. A Cubic-regularized Policy Newton Algorithm for Reinforcement Learning

       2. Reinforcement Learning with an Abrupt Model Change

   14. Offline RL

       1. Using Offline Data to Speed-up Reinforcement Learning in Procedurally Generated Environments

   15. Optimization applications

       1. Debiasing Conditional Stochastic Optimization

   16. Planning

       1. A Review of Symbolic, Subsymbolic and Hybrid Methods for Sequential Decision Making INT

   17. Quantum Computing

       1. Deep Reinforcement Learning Using Hybrid Quantum Neural Network

       2. Quantum deep Q learning with distributed prioritized experience replay

       3. Sample-efficient Model-based Reinforcement Learning for Quantum Control

   18. Risk-sensitive/safe/constrained RL

       1. Approximate Shielding of Atari Agents for Safe Exploration

       2. Feasible Policy Iteration

       3. Safety Guaranteed Manipulation Based on Reinforcement Learning Planner and Model Predictive Control Actor

   19. Robust RL

       1. Robust Deep Reinforcement Learning Scheduling via Weight Anchoring

       2. Robust Route Planning with Distributional Reinforcement Learning in a Stochastic Road Network Environment

       3. Robust nonlinear set-point control with reinforcement learning

   20. Reward Optimization

       1. Provably Feedback-Efficient Reinforcement Learning via Active Reward Learning

   21. Temporal Difference Learning

       1. Efficient Deep Reinforcement Learning Requires Regulating Overfitting

   22. Transformers

       1. Hyper-Decision Transformer for Efficient Online Policy Adaptation

       2. Pointerformer: Deep Reinforced Multi-Pointer Transformer for the Traveling Salesman Problem

3. Education

   1. Leveraging Deep Reinforcement Learning for Metacognitive Interventions across Intelligent Tutoring Systems INT

4. Financial Applications

   1. Learning policies for resource allocation in business processes

5. Games and Game Theory

   1. Mastering Asymmetrical Multiplayer Game with Multi-Agent Asymmetric-Evolution Reinforcement Learning INT

6. Physics

   1. How to Control Hydrodynamic Force on Fluidic Pinball via Deep Reinforcement Learning

   2. TempoRL: laser pulse temporal shape optimization with Deep Reinforcement Learning

7. Ethics

   1. Boosting Theory-of-Mind Performance in Large Language Models via Prompting INT

   2. Long-Term Fairness with Unknown Dynamics

8. Healthcare Applications

   1. Alzheimers Disease Diagnosis using Machine Learning: A Review INT

   2. Model Based Reinforcement Learning for Personalized Heparin Dosing INT

   3. Token Imbalance Adaptation for Radiology Report Generation

9. Natural Language Processing

   1. Think Before You Act: Unified Policy for Interleaving Language Reasoning with Actions

10. Mathematics

    1. Searching for ribbons with machine learning

See you next week!

See you next week