Optimising Human-AI Collaboration by Learning Convincing Explanations
- URL: http://arxiv.org/abs/2311.07426v1
- Date: Mon, 13 Nov 2023 16:00:16 GMT
- Title: Optimising Human-AI Collaboration by Learning Convincing Explanations
- Authors: Alex J. Chan, Alihan Huyuk, Mihaela van der Schaar
- Abstract summary: We propose a method for a collaborative system that remains safe by having a human making decisions.
Ardent enables efficient and effective decision-making by adapting to individual preferences for explanations.
- Score: 62.81395661556852
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Machine learning models are being increasingly deployed to take, or assist in
taking, complicated and high-impact decisions, from quasi-autonomous vehicles
to clinical decision support systems. This poses challenges, particularly when
models have hard-to-detect failure modes and are able to take actions without
oversight. In order to handle this challenge, we propose a method for a
collaborative system that remains safe by having a human ultimately making
decisions, while giving the model the best opportunity to convince and debate
them with interpretable explanations. However, the most helpful explanation
varies among individuals and may be inconsistent across stated preferences. To
this end we develop an algorithm, Ardent, to efficiently learn a ranking
through interaction and best assist humans complete a task. By utilising a
collaborative approach, we can ensure safety and improve performance while
addressing transparency and accountability concerns. Ardent enables efficient
and effective decision-making by adapting to individual preferences for
explanations, which we validate through extensive simulations alongside a user
study involving a challenging image classification task, demonstrating
consistent improvement over competing systems.
Related papers
- Combining AI Control Systems and Human Decision Support via Robustness and Criticality [53.10194953873209]
We extend a methodology for adversarial explanations (AE) to state-of-the-art reinforcement learning frameworks.
We show that the learned AI control system demonstrates robustness against adversarial tampering.
In a training / learning framework, this technology can improve both the AI's decisions and explanations through human interaction.
arXiv Detail & Related papers (2024-07-03T15:38:57Z) - Analyzing Operator States and the Impact of AI-Enhanced Decision Support
in Control Rooms: A Human-in-the-Loop Specialized Reinforcement Learning
Framework for Intervention Strategies [0.9378955659006951]
In complex industrial and chemical process control rooms, effective decision-making is crucial for safety andeffi- ciency.
The experiments in this paper evaluate the impact and applications of an AI-based decision support system integrated into an improved human-machine interface.
arXiv Detail & Related papers (2024-02-20T18:31:27Z) - RLIF: Interactive Imitation Learning as Reinforcement Learning [56.997263135104504]
We show how off-policy reinforcement learning can enable improved performance under assumptions that are similar but potentially even more practical than those of interactive imitation learning.
Our proposed method uses reinforcement learning with user intervention signals themselves as rewards.
This relaxes the assumption that intervening experts in interactive imitation learning should be near-optimal and enables the algorithm to learn behaviors that improve over the potential suboptimal human expert.
arXiv Detail & Related papers (2023-11-21T21:05:21Z) - Assisting Human Decisions in Document Matching [52.79491990823573]
We devise a proxy matching task that allows us to evaluate which kinds of assistive information improve decision makers' performance.
We find that providing black-box model explanations reduces users' accuracy on the matching task.
On the other hand, custom methods that are designed to closely attend to some task-specific desiderata are found to be effective in improving user performance.
arXiv Detail & Related papers (2023-02-16T17:45:20Z) - Blessing from Human-AI Interaction: Super Reinforcement Learning in
Confounded Environments [19.944163846660498]
We introduce the paradigm of super reinforcement learning that takes advantage of Human-AI interaction for data driven sequential decision making.
In the decision process with unmeasured confounding, the actions taken by past agents can offer valuable insights into undisclosed information.
We develop several super-policy learning algorithms and systematically study their theoretical properties.
arXiv Detail & Related papers (2022-09-29T16:03:07Z) - Inverse Online Learning: Understanding Non-Stationary and Reactionary
Policies [79.60322329952453]
We show how to develop interpretable representations of how agents make decisions.
By understanding the decision-making processes underlying a set of observed trajectories, we cast the policy inference problem as the inverse to this online learning problem.
We introduce a practical algorithm for retrospectively estimating such perceived effects, alongside the process through which agents update them.
Through application to the analysis of UNOS organ donation acceptance decisions, we demonstrate that our approach can bring valuable insights into the factors that govern decision processes and how they change over time.
arXiv Detail & Related papers (2022-03-14T17:40:42Z) - Improving Human Sequential Decision-Making with Reinforcement Learning [29.334511328067777]
We design a novel machine learning algorithm that is capable of extracting "best practices" from trace data.
Our algorithm selects the tip that best bridges the gap between the actions taken by human workers and those taken by the optimal policy.
Experiments show that the tips generated by our algorithm can significantly improve human performance.
arXiv Detail & Related papers (2021-08-19T02:57:58Z) - End-to-End Learning and Intervention in Games [60.41921763076017]
We provide a unified framework for learning and intervention in games.
We propose two approaches, respectively based on explicit and implicit differentiation.
The analytical results are validated using several real-world problems.
arXiv Detail & Related papers (2020-10-26T18:39:32Z) - Automatic Discovery of Interpretable Planning Strategies [9.410583483182657]
We introduce AI-Interpret, a method for transforming idiosyncratic policies into simple and interpretable descriptions.
We show that prividing the decision rules generated by AI-Interpret as flowcharts significantly improved people's planning strategies and decisions.
arXiv Detail & Related papers (2020-05-24T12:24:52Z) - A New Framework for Query Efficient Active Imitation Learning [5.167794607251493]
There is a human expert knowing the rewards and unsafe states based on his preference and objective, but querying that human expert is expensive.
We propose a new framework for imitation learning (IL) algorithm that actively and interactively learns a model of the user's reward function with efficient queries.
We evaluate the proposed method with simulated human on a state-based 2D navigation task, robotic control tasks and the image-based video games.
arXiv Detail & Related papers (2019-12-30T18:12:27Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.