RL Algorithm

Reinforcement learning (RL) algorithms aim to train agents to make optimal decisions in dynamic environments by learning from trial and error. Current research focuses on improving sample efficiency and generalization, exploring techniques like contrastive learning for exploration, incorporating graph attention mechanisms for structured problem solving (e.g., in geometric reasoning), and leveraging prior knowledge through reward machines or self-paced learning to guide the learning process. These advancements are leading to more efficient and robust RL agents applicable to diverse domains, including robotics and education, where they can automate complex tasks and improve decision-making processes.

Papers

October 29, 2024

Human-Readable Programs as Actors of Reinforcement Learning Agents Using Critic-Moderated Evolution
Senne Deproost, Denis Steckelmacher, Ann Nowé
Deep Reinforcement Learning Black Box Reinforcement Learning Agent Critic Model Actor Loss Programmatic Reinforcement Learning RL Algorithm

October 19, 2024

Offline-to-online Reinforcement Learning for Image-based Grasping with Scarce Demonstrations
Bryan Chan, Anson Leung, James Bergstra
Behavior Cloning Suboptimal Demonstration Policy Actor Critic Offline to Online Reinforcement Learning RL Algorithm

August 11, 2024

A Single Goal is All You Need: Skills and Exploration Emerge from Contrastive RL without Rewards, Demonstrations, or Subgoals
Grace Liu, Michael Tang, Benjamin Eysenbach
Environment Exploration Reward Function Manipulation Task Noisy Demonstration Active Exploration Pseudo Goal Robust Skill Contrastive Reinforcement Learning RL Algorithm

March 14, 2024

Incorporating Graph Attention Mechanism into Geometric Problem Solving Based on Deep Reinforcement Learning
Xiuqin Zhong, Shengyuan Yan, Gongqi Lin, Hongguang Fu, Liang Xu, Siwen Jiang, Lei Huang, Wei Fang
Artificial Intelligence Deep Reinforcement Learning Automatic Solver Graph Attention Mechanism Geometry Problem General Artificial Intelligence Strategy Synthesis RL Algorithm

September 18, 2023

Contrastive Initial State Buffer for Reinforcement Learning
Nico Messikommer, Yunlong Song, Davide Scaramuzza
Reinforcement Learning Complex Robotic Task RL Algorithm

May 25, 2023

Reward-Machine-Guided, Self-Paced Reinforcement Learning
Cevahir Koprulu, Ufuk Topcu
Reward Learning RL Algorithm

November 27, 2022

Eluder-based Regret for Stochastic Contextual MDPs
Orin Levy, Asaf Cassel, Alon Cohen, Yishay Mansour
Optimal Regret Stochastic Way Regret Minimization Contextual Markov Decision Process Contextual MDPs RL Algorithm

October 21, 2022

Continual Vision-based Reinforcement Learning with Group Symmetries
Shiqi Liu, Mengdi Xu, Piede Huang, Yongkang Liu, Kentaro Oguchi, Ding Zhao
Continual Reinforcement Learning RL Algorithm

January 21, 2022

Meta Learning MDPs with Linear Transition Models
Robert Müller, Aldo Pacchiano
Markov Decision Process Task Distribution Meta Reinforcement Transition Model RL Algorithm