Human-in-the-loop reinforcement learning: A survey and position on requirements, challenges, and opportunities

CO Retzlaff, S Das, C Wayllace, P Mousavi… - Journal of Artificial …, 2024 - jair.org
Artificial intelligence (AI) and especially reinforcement learning (RL) have the potential to
enable agents to learn and perform tasks autonomously with superhuman performance …

A survey on explainable reinforcement learning: Concepts, algorithms, challenges

Y Qing, S Liu, J Song, H Wang, M Song - arxiv preprint arxiv:2211.06665, 2022 - arxiv.org
Reinforcement Learning (RL) is a popular machine learning paradigm where intelligent
agents interact with the environment to fulfill a long-term goal. Driven by the resurgence of …

Symbols as a lingua franca for bridging human-ai chasm for explainable and advisable ai systems

S Kambhampati, S Sreedharan, M Verma… - Proceedings of the …, 2022 - ojs.aaai.org
Despite the surprising power of many modern AI systems that often learn their own
representations, there is significant discontent about their inscrutability and the attendant …

Safe driving via expert guided policy optimization

Z Peng, Q Li, C Liu, B Zhou - Conference on Robot Learning, 2022 - proceedings.mlr.press
When learning common skills like driving, beginners usually have domain experts standing
by to ensure the safety of the learning process. We formulate such learning scheme under …

[BOOK][B] Explainable human-AI interaction: A planning perspective

S Sreedharan, A Kulkarni, S Kambhampati - 2022 - books.google.com
From its inception, artificial intelligence (AI) has had a rather ambivalent relationship with
humans—swinging between their augmentation and replacement. Now, as AI technologies …

hmos: An extensible platform for task-oriented human–machine computing

H Wang, Z Yu, Y Zhang, Y Wang, F Yang… - … on Human-Machine …, 2024 - ieeexplore.ieee.org
With rapid advancements in artificial intelligence (AI) technologies, AI-powered machines
are increasingly capable of collaborating with humans to enhance decision-making in …

Exploiting Unlabeled Data for Feedback Efficient Human Preference based Reinforcement Learning

M Verma, S Bhambri, S Kambhampati - arxiv preprint arxiv:2302.08738, 2023 - arxiv.org
Preference Based Reinforcement Learning has shown much promise for utilizing human
binary feedback on queried trajectory pairs to recover the underlying reward model of the …

A survey on enhancing reinforcement learning in complex environments: Insights from human and llm feedback

AR Laleh, MN Ahmadabadi - arxiv preprint arxiv:2411.13410, 2024 - arxiv.org
Reinforcement learning (RL) is one of the active fields in machine learning, demonstrating
remarkable potential in tackling real-world challenges. Despite its promising prospects, this …

Data Driven Reward Initialization for Preference based Reinforcement Learning

M Verma, S Kambhampati - arxiv preprint arxiv:2302.08733, 2023 - arxiv.org
Preference-based Reinforcement Learning (PbRL) methods utilize binary feedback from the
human in the loop (HiL) over queried trajectory pairs to learn a reward model in an attempt …

Explainable and adaptable augmentation in knowledge attention network for multi-agent deep reinforcement learning systems

J Ho, CM Wang - 2020 IEEE Third International Conference on …, 2020 - ieeexplore.ieee.org
The scale of modem Artificial Intelligence systems has been growing and entering more
research territories by incorporating Deep Learning (DL) and Deep Reinforcement Learning …