# Autonomous Goal Detection and Cessation in Reinforcement Learning: A Case Study on Source Term Estimation

arXiv: https://arxiv.org/abs/2409.09541 · HTML: https://mlsanity.com/paper/2409.09541/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods.
- Builds on 10 of its 32 references that are in the map.
- First posted on arXiv 14 Sep 2024.

## Placed in

- Deep reinforcement learning methods / [Deep RL algorithms and representations](https://mlsanity.com/deeprl/deep-rl-algorithms-and-representations/)

## Builds on (most cited first, 10 of 10)

- [End-to-End Training of Deep Visuomotor Policies](https://mlsanity.com/paper/1504.00702/) (2015)
- [Deep Reinforcement Learning for Autonomous Driving: A Survey](https://mlsanity.com/paper/2002.00444/) (2020)
- [Cooperative Open-ended Learning Framework for Zero-shot Coordination](https://mlsanity.com/paper/2302.04831/) (2023)
- [Model-based Multi-agent Policy Optimization with Adaptive Opponent-wise Rollouts](https://mlsanity.com/paper/2105.03363/) (2021)
- [Order Matters: Agent-by-agent Policy Optimization](https://mlsanity.com/paper/2302.06205/) (2023)
- [ZSC-Eval: An Evaluation Toolkit and Benchmark for Multi-agent Zero-shot Coordination](https://mlsanity.com/paper/2310.05208/) (2023)
- [Model-based Multi-agent Reinforcement Learning: Recent Progress and Prospects](https://mlsanity.com/paper/2203.10603/) (2022)
- [Tackling Cooperative Incompatibility for Zero-Shot Human-AI Coordination](https://mlsanity.com/paper/2306.03034/) (2023)
- [Beyond Local Views: Global State Inference with Diffusion Models for Cooperative Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2408.09501/) (2024)
- [Dual Control for Exploitation and Exploration (DCEE) in Autonomous Search](https://mlsanity.com/paper/2012.06276/) (2020)

## Built on by (most cited first, 6 of 6)

- [RAT: Adversarial Attacks on Deep Reinforcement Agents for Targeted Behaviors](https://mlsanity.com/paper/2412.10713/) (2024)
- [Belief-Contraction-Driven Active Inverse Source Localization and Characterization](https://mlsanity.com/paper/2501.13084/) (2025)
- [TriShGAN: Enhancing Sparsity and Robustness in Multivariate Time Series Counterfactuals Explanation](https://mlsanity.com/paper/2511.06529/) (2025)
- [Dynamic Correction of Erroneous State Estimates via Diffusion Bayesian Exploration](https://mlsanity.com/paper/2512.03102/) (2025)
- [Distill-Belief: Closed-Loop Inverse Source Localization and Characterization in Physical Fields](https://mlsanity.com/paper/2604.26095/) (2026)
- [CIG-RL: Curiosity-Driven Information-Guided Reinforcement Learning for Source Term Estimation in Uncertain Environments](https://mlsanity.com/paper/2608.30673/) (2026)

## Abstract (arXiv)

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 gradient algorithms, and evaluated its performance on the Source Term Estimation problem. The experimental results showed that AGDC-enhanced RL algorithms significantly outperformed traditional statistical methods such as infotaxis, entrotaxis, and dual control for exploitation and exploration, as well as a non-statistical random action selection method. These improvements were evident in terms of success rate, mean traveled distance, and search time, highlighting AGDC's effectiveness and efficiency in complex, real-world scenarios.