paper-with-me

홈 › Papers

The Courage to Stop: Overcoming Sunk Cost Fallacy in Deep Reinforcement Learning

2025-06-16 · Jiashun Liu, Johan Obando-Ceron, Pablo Samuel Castro, Aaron Courville, Ling Pan

Off-policy deep reinforcement learning (RL) typically leverages replay buffers for reusing past experiences during learning. This can help improve sample efficiency when the collected data is informative and aligned with the learning objectives; when that is not the case, it can have the effect of "polluting" the replay buffer with data which can exacerbate optimization challenges in addition to wasting environment interactions due to wasteful sampling. We argue that sampling these uninformative and wasteful transitions can be avoided by addressing the sunk cost fallacy, which, in the context of deep RL, is the tendency towards continuing an episode until termination. To address this, we propose learn to stop (LEAST), a lightweight mechanism that enables strategic early episode termination based on Q-value and gradient statistics, which helps agents recognize when to terminate unproductive episodes early. We demonstrate that our method improves learning efficiency on a variety of RL algorithms, evaluated on both the MuJoCo and DeepMind Control Suite benchmarks.

📄 PDF Abstract BibTeX arXiv:2506.13672

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Reinforcement LearningMuJoCoReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Heuristics and Biases in AI Decision-Making: Implications for Responsible AGI

2024-09-26 · Payam Saeedi, Mahsa Goodarzi, M Abdullah Canbaz

We investigate the presence of cognitive biases in three large language models (LLMs): GPT-4o, Gemma 2, and Llama 3.1. The study uses 1,500 experiments across nine established cognitive biases to evaluate the models' res…

Decision Making

Mislearning from Censored Data: The Gambler's Fallacy and Other Correlational Mistakes in Optimal-Stopping Problems

2018-03-21 · Kevin He

I study endogenous learning dynamics for people who misperceive intertemporal correlations in random sequences. Biased agents face an optimal-stopping problem. They are uncertain about the underlying distribution and lea…

On an Irreversible Investment Problem with Two-Factor Uncertainty

2021-03-15 · Felix Dammann, Giorgio Ferrari

We consider a real options model for the optimal irreversible investment problem of a profit maximizing company. The company has the opportunity to invest into a production plant capable of producing two products, of whi…

Vocal Bursts Valence Prediction

RADAMS: Resilient and Adaptive Alert and Attention Management Strategy against Informational Denial-of-Service (IDoS) Attacks

2021-11-01 · Linan Huang, Quanyan Zhu

Attacks exploiting human attentional vulnerability have posed severe threats to cybersecurity. In this work, we identify and formally define a new type of proactive attentional attacks called Informational Denial-of-Serv…

Decision MakingManagement

Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpoints

2022-12-09 · Aran Komatsuzaki, Joan Puigcerver, James Lee-Thorp, Carlos Riquelme Ruiz 외

Training large, deep neural networks to convergence can be prohibitively expensive. As a result, often only a small selection of popular, dense models are reused across different contexts and tasks. Increasingly, sparsel…

Mixture-of-Experts