Autonomous Goal Detection And Cessation In Reinforcement Learning: A Case Study On Source Term Estimation

Abstract

Reinforcement Learning has revolutionized decision-making processes in dynamic environments, yet it often struggles with autonomously detecting and achieving goals without clear feedback signals. For example, in a Source Term Estimation problem, the lack of precise environmental information makes it challenging to provide clear feedback signals and to define and evaluate how the source's location is determined. To address this challenge, the Autonomous Goal Detection and Cessation (AGDC) module was developed, enhancing various RL algorithms by incorporating a self-feedback mechanism for autonomous goal detection and cessation upon task completion. Our method effectively identifies and ceases undefined goals by approximating the agent's belief, significantly enhancing the capabilities of RL algorithms in environments with limited feedback. To validate effectiveness of our approach, we integrated AGDC with deep Q-Network, proximal policy optimization, and deep deterministic policy gradie

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyshi2024autonomous

Related papers

• Towards Measuring Goal-directedness In AI Systems (2024)0.00
• Self-supervised Goal-reaching Results In Multi-agent Cooperation And Exploration (2025)0.00
• Unified Algorithms For RL With Decision-estimation Coefficients: PAC, Reward-free, Preference-based Learning, And Beyond (2022)5.24
• Goal Recognition As Reinforcement Learning (2022)6.34
• Adviser-actor-critic: Eliminating Steady-state Error In Reinforcement Learning Control (2025)0.00
• Autoeg: Automated Experience Grafting For Off-policy Deep Reinforcement Learning (2020)0.00
• Learning To Explore When Mistakes Are Not Allowed (2025)0.00
• C-learning: Learning To Achieve Goals Via Recursive Classification (2020)0.00