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

July 5, 2024

Unified continuous-time q-learning for mean-field game and mean-field control problems
Xiaoli Wei, Xiang Yu, Fengyi Yuan
Reinforcement Learning Q Learning Mean Field Unified Alignment Mean Field Game
Using Petri Nets as an Integrated Constraint Mechanism for Reinforcement Learning Tasks
Timon Sachweh, Pierre Haritz, Thomas Liebig
Reinforcement Learning Trustworthy Artificial Intelligence Reinforcement Learning Task Petri Net Constraint Model Agent State PNPic Model
Enhancing Safety for Autonomous Agents in Partly Concealed Urban Traffic Environments Through Representation-Based Shielding
Pierre Haritz, David Wanke, Thomas Liebig
Reinforcement Learning Autonomous Navigation Autonomous Agent Traffic Management Unsignalized Intersection Traffic Environment Enhancing Safety Model Based Shielding
Gradient-based Regularization for Action Smoothness in Robotic Control with Reinforcement Learning
I Lee, Hoang-Giang Cao, Cong-Tinh Dao, Yu-Cheng Chen, I-Chen Wu
Reinforcement Learning Deep Reinforcement Learning Reinforcement Learning Algorithm Robot Control Smooth Animation Action Correction
Unsupervised Video Summarization via Reinforcement Learning and a Trained Evaluator
Mehryar Abbasi, Hadi Hadizadeh, Parvaneh Saeedi
Reinforcement Learning Video Generation Human Evaluation Video Summarization
PA-LOCO: Learning Perturbation-Adaptive Locomotion for Quadruped Robots
Zhiyuan Xiao, Xinyu Zhang, Xiang Zhou, Qingrui Zhang
Reinforcement Learning Quadruped Robot Robust Locomotion Quadrupedal Locomotion Privileged Information Locomotion Strategy Blind Locomotion
Autoverse: An Evolvable Game Language for Learning Robust Embodied Agents
Sam Earle, Julian Togelius
Reinforcement Learning Imitation Learning Open Ended Evolutionary Game Puzzle Game

July 4, 2024

Craftium: An Extensible Framework for Creating Reinforcement Learning Environments
Mikel Malagón, Josu Ceberio, Jose A. Lozano
Reinforcement Learning Reinforcement Learning Environment Traditional CrAFT Extensible Framework
Improving Sample Efficiency of Reinforcement Learning with Background Knowledge from Large Language Models
Fuxiang Zhang, Junyou Li, Yi-Chen Li, Zongzhang Zhang, Yang Yu, Deheng Ye
Language Model Reinforcement Learning Optimal Policy Policy Learning Reward Shaping Sample Efficiency Background Knowledge
Continuous-time q-Learning for Jump-Diffusion Models under Tsallis Entropy
Lijun Bo, Yijie Huang, Xiang Yu, Tingting Zhang
Reinforcement Learning Q Learning Optimal Policy Martingale Difference Jump Diffusion Tsallis Entropy
Q-Adapter: Customizing Pre-trained LLMs to New Preferences with Forgetting Mitigation
Yi-Chen Li, Fuxiang Zhang, Wenjie Qiu, Lei Yuan, Chengxing Jia, Zongzhang Zhang, Yang Yu, Bo An
Reinforcement Learning Q Function Domain Specific Task LLM Adaptation

July 3, 2024

Efficient Imitation Without Demonstrations via Value-Penalized Auxiliary Control from Examples
Trevor Ablett, Bryan Chan, Jayce Haoran Wang, Jonathan Kelly
Reinforcement Learning LeArning Abstract Reward Function Noisy Demonstration Reward Report Fewer Example Auxiliary Loss Auxiliary Feature Gradient Penalty
RobocupGym: A challenging continuous control benchmark in Robocup
Michael Beukman, Branden Ingram, Geraud Nangue Tasse, Benjamin Rosman, Pravesh Ranchod
Reinforcement Learning Robocup SPL Control Benchmark
Reinforcement Learning for Sequence Design Leveraging Protein Language Models
Jithendaraa Subramanian, Shivakanth Sujit, Niloy Irtisam, Umong Sain, Riashat Islam, Derek Nowrouzezahrai, Samira Ebrahimi Kahou
Reinforcement Learning Protein Sequence Protein Language Model Protein Design Sequence Design Protein Sequence Design
Warm-up Free Policy Optimization: Improved Regret in Linear Markov Decision Processes
Asaf Cassel, Aviv Rosenberg
Reinforcement Learning Policy OpTimization Regret Analysis Rate Optimal Regret
On the Client Preference of LLM Fine-tuning in Federated Learning
Feijie Wu, Xiaoze Liu, Haoyu Wang, Xingchen Wang, Jing Gao
Large Language Model Reinforcement Learning Preference Feedback Human Preference Preference Datasets Model Completion

July 2, 2024

PWM: Policy Learning with Large World Models
Ignat Georgiev, Varun Giridhar, Nicklas Hansen, Animesh Garg
Reinforcement Learning Large Model First Order Policy
Reinforcement Learning and Machine ethics:a systematic review
Ajay Vishwanath, Louise A. Dennis, Marija Slavkovik
Reinforcement Learning Systematic Review Ethical Behavior Machine Ethic
Physics-Informed Model and Hybrid Planning for Efficient Dyna-Style Reinforcement Learning
Zakariae El Asri, Olivier Sigaud, Nicolas Thome
Reinforcement Learning Efficient Reinforcement Learning Hierarchical Planning Physic Aware Model Free Policy Hybrid Planning Physical Knowledge
Cost-Effective Proxy Reward Model Construction with On-Policy and Active Learning
Yifang Chen, Shuohang Wang, Ziyi Yang, Hiteshi Sharma, Nikos Karampatziakis, Donghan Yu, Kevin Jamieson, Simon Shaolei Du, Yelong Shen
Reinforcement Learning Active Learning Direct Preference Optimization Preference Feedback Health Policy Recommendation Offline Preference Proxy Reward

Reinforcement Learning

Papers

Unified continuous-time q-learning for mean-field game and mean-field control problems

Using Petri Nets as an Integrated Constraint Mechanism for Reinforcement Learning Tasks

Enhancing Safety for Autonomous Agents in Partly Concealed Urban Traffic Environments Through Representation-Based Shielding

Gradient-based Regularization for Action Smoothness in Robotic Control with Reinforcement Learning

Unsupervised Video Summarization via Reinforcement Learning and a Trained Evaluator

PA-LOCO: Learning Perturbation-Adaptive Locomotion for Quadruped Robots

Autoverse: An Evolvable Game Language for Learning Robust Embodied Agents

Craftium: An Extensible Framework for Creating Reinforcement Learning Environments

Improving Sample Efficiency of Reinforcement Learning with Background Knowledge from Large Language Models

Continuous-time q-Learning for Jump-Diffusion Models under Tsallis Entropy

Q-Adapter: Customizing Pre-trained LLMs to New Preferences with Forgetting Mitigation

Efficient Imitation Without Demonstrations via Value-Penalized Auxiliary Control from Examples

RobocupGym: A challenging continuous control benchmark in Robocup

Reinforcement Learning for Sequence Design Leveraging Protein Language Models

Warm-up Free Policy Optimization: Improved Regret in Linear Markov Decision Processes

On the Client Preference of LLM Fine-tuning in Federated Learning

PWM: Policy Learning with Large World Models

Reinforcement Learning and Machine ethics:a systematic review

Physics-Informed Model and Hybrid Planning for Efficient Dyna-Style Reinforcement Learning

Cost-Effective Proxy Reward Model Construction with On-Policy and Active Learning