Goal Oriented Reinforcement Learning

Goal-oriented reinforcement learning (RL) focuses on training agents to achieve specific goals, optimizing for efficiency and success rate rather than simply maximizing cumulative rewards. Current research emphasizes efficient exploration strategies, particularly in scenarios with sparse or delayed feedback, utilizing techniques like subgoal generation, intrinsic reward shaping (e.g., via distance metrics), and adaptive reward transitions (e.g., from sparse to dense). These advancements are improving sample efficiency and robustness in applications ranging from robotics and online education to multi-agent systems, addressing challenges like non-stationary environments and the need for less expert-dependent training data.

Papers

September 14, 2024

Learning Nudges for Conditional Cooperation: A Multi-Agent Reinforcement Learning Model
Shatayu Kulkarni, Sabine Brunswicker
Multi Agent Reinforcement Learning Digital Algorithmic Nudging Goal Oriented Reinforcement Learning Public Good Game

September 6, 2024

Goal-Reaching Policy Learning from Non-Expert Observations via Effective Subgoal Guidance
RenMing Huang, Shaochong Liu, Yunqiang Pei, Peng Wang, Guoqing Wang, Yang Yang, Hengtao Shen
Efficient Exploration Policy Actor Critic Subgoal Search Goal Oriented Reinforcement Learning

June 29, 2024

Revisiting Sparse Rewards for Goal-Reaching Reinforcement Learning
Gautham Vasan, Yan Wang, Fahim Shahriar, James Bergstra, Martin Jagersand, A. Rupam Mahmood
Robot Learning Sparse Reward Episodic Reinforcement Learning Conditioned Policy Goal Oriented Reinforcement Learning

March 11, 2024

Unveiling the Significance of Toddler-Inspired Reward Transition in Goal-Oriented Reinforcement Learning
Junseok Park, Yoonsung Kim, Hee Bin Yoo, Min Whoo Lee, Kibeom Kim, Won-Seok Choi, Minsu Lee, Byoung-Tak Zhang
Reinforcement Learning Importance Aware Dense Reward Goal Oriented Reinforcement Learning Reward Transition

December 3, 2023

Towards Goal-oriented Intelligent Tutoring Systems in Online Education
Yang Deng, Zifeng Ren, An Zhang, Wenqiang Lei, Tat-Seng Chua
Intelligent Tutoring System Graph Reinforcement Learning Online Training Interactive Planning Goal Oriented Reinforcement Learning

October 31, 2023

Autonomous Robotic Reinforcement Learning with Asynchronous Human Feedback
Max Balsells, Marcel Torne, Zihan Wang, Samedh Desai, Pulkit Agrawal, Abhishek Gupta
Continual Learning Real World Reinforcement Learning Robot Experience Goal Oriented Reinforcement Learning Autonomous Reinforcement Learning

May 8, 2023

Goal-oriented inference of environment from redundant observations
Kazuki Takahashi, Tomoki Fukai, Yutaka Sakai, Takashi Takekawa
Reinforcement Learning Environment Feature Information Redundancy Observable Markov Decision Process Optimal Behavior Goal Oriented Reinforcement Learning Goal Inference

April 3, 2023

Optimal Goal-Reaching Reinforcement Learning via Quasimetric Learning
Tongzhou Wang, Antonio Torralba, Phillip Isola, Amy Zhang
Optimal Value Function Goal Oriented Reinforcement Learning Quasimetric Learning

October 3, 2022

CostNet: An End-to-End Framework for Goal-Directed Reinforcement Learning
Per-Arne Andersen, Morten Goodwin, Ole-Christoffer Granmo
Reinforcement Learning End to End Model Free Reinforcement Learning Novel Reinforcement Learning Goal Oriented Reinforcement Learning

June 10, 2022

Offline Stochastic Shortest Path: Learning, Evaluation and Towards Optimality
Ming Yin, Wenjing Chen, Mengdi Wang, Yu-Xiang Wang
LeArning Abstract Global Evaluation Near Optimality Shortest Path Stochastic Shortest Path Offline Policy Evaluation Goal Oriented Reinforcement Learning Optimal Offline

May 25, 2022

Near-Optimal Goal-Oriented Reinforcement Learning in Non-Stationary Environments
Liyu Chen, Haipeng Luo
Optimal Policy Finite Horizon Non Stationary Environment Goal Oriented Reinforcement Learning Dynamic Regret Minimization