Interleaving Fast and Slow Decision Making

• URL: http://arxiv.org/abs/2010.16244v2
• Date: Fri, 26 Mar 2021 16:49:24 GMT
• Title: Interleaving Fast and Slow Decision Making
• Authors: Aditya Gulati, Sarthak Soni, Shrisha Rao
• Abstract summary: Kahneman proposes that we use two different styles of thinking -- a fast and intuitive System 1 for certain tasks, along with a slower but more analytical System 2 for others. We propose a novel and general framework which includes a new System 0 to oversee Systems 1 and 2. We evaluate such a framework on a modified version of the classic Pac-Man game, with an already-trained RL algorithm for System 1, a Monte-Carlo tree search for System 2, and several different possible strategies for System 0.
• Score: 7.41244589428771
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: The "Thinking, Fast and Slow" paradigm of Kahneman proposes that we use two different styles of thinking -- a fast and intuitive System 1 for certain tasks, along with a slower but more analytical System 2 for others. While the idea of using this two-system style of thinking is gaining popularity in AI and robotics, our work considers how to interleave the two styles of decision-making, i.e., how System 1 and System 2 should be used together. For this, we propose a novel and general framework which includes a new System 0 to oversee Systems 1 and 2. At every point when a decision needs to be made, System 0 evaluates the situation and quickly hands over the decision-making process to either System 1 or System 2. We evaluate such a framework on a modified version of the classic Pac-Man game, with an already-trained RL algorithm for System 1, a Monte-Carlo tree search for System 2, and several different possible strategies for System 0. As expected, arbitrary switches between Systems 1 and 2 do not work, but certain strategies do well. With System 0, an agent is able to perform better than one that uses only System 1 or System 2.

Related papers

• System-1.x: Learning to Balance Fast and Slow Planning with Language Models [68.77277620915143]
  Language models can be used to solve long-horizon planning problems in two distinct modes. A fast 'System-1' mode, directly generating plans without any explicit search or backtracking, and a slow 'System-2' mode, planning step-by-step. We propose the System-1.x Planner, a controllable planning framework with LLMs.
  arXiv  Detail & Related papers  (2024-07-19T15:40:59Z)
• Distilling System 2 into System 1 [35.194258450176534]
  Large language models (LLMs) can spend extra compute during inference to generate intermediate thoughts. We show that several such techniques can be successfully distilled, resulting in improved results compared to the original System 1 performance.
  arXiv  Detail & Related papers  (2024-07-08T15:17:46Z)
• Fast and Slow Generating: An Empirical Study on Large and Small Language Models Collaborative Decoding [27.004817441034795]
  Collaborative decoding between large and small language models (SLMs) presents a promising strategy to mitigate these issues. Inspired by dual-process cognitive theory, we propose a unified framework, termed Fast and Slow Generating (FS-GEN) Within this framework, LLMs are categorized as System 2 (slow and deliberate), while independent SLMs are designated as System 1.
  arXiv  Detail & Related papers  (2024-06-18T05:59:28Z)
• System-2 Recommenders: Disentangling Utility and Engagement in Recommendation Systems via Temporal Point-Processes [80.97898201876592]
  We propose a generative model in which past content interactions impact the arrival rates of users based on a self-exciting Hawkes process. We show analytically that given samples it is possible to disentangle System-1 and System-2 and allow content optimization based on user utility.
  arXiv  Detail & Related papers  (2024-05-29T18:19:37Z)
• AAAI 2022 Fall Symposium: System-1 and System-2 realized within the Common Model of Cognition [0.0]
  We situating System-1 and System-2 within the Common Model of Cognition. Results show that what are thought to be distinctive characteristics of System-1 and 2 instead form a spectrum of cognitive properties.
  arXiv  Detail & Related papers  (2023-05-16T01:28:06Z)
• Fast and Slow Planning [25.91512962807549]
  SOFAI exploits multiple solving approaches, with different capabilities that characterize them as either fast or slow, and a metacognitive module to regulate them. The behavior of this system is then compared to state-of-the-art solvers, showing that the newly introduced system presents better results in terms of generality.
  arXiv  Detail & Related papers  (2023-03-07T23:05:38Z)
• Learning Connectivity-Maximizing Network Configurations [123.01665966032014]
  We propose a supervised learning approach with a convolutional neural network (CNN) that learns to place communication agents from an expert. We demonstrate the performance of our CNN on canonical line and ring topologies, 105k randomly generated test cases, and larger teams not seen during training. After training, our system produces connected configurations 2 orders of magnitude faster than the optimization-based scheme for teams of 10-20 agents.
  arXiv  Detail & Related papers  (2021-12-14T18:59:01Z)
• Learning Physical Concepts in Cyber-Physical Systems: A Case Study [72.74318982275052]
  We provide an overview of the current state of research regarding methods for learning physical concepts in time series data. We also analyze the most important methods from the current state of the art using the example of a three-tank system.
  arXiv  Detail & Related papers  (2021-11-28T14:24:52Z)
• Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoning [49.6928533575956]
  We use neural inference to mediate between the neural System 1 and the logical System 2. Results in robust story generation and grounded instruction-following show that this approach can increase the coherence and accuracy of neurally-based generations.
  arXiv  Detail & Related papers  (2021-07-06T17:59:49Z)
• Joint System-Wise Optimization for Pipeline Goal-Oriented Dialog System [76.22810715401147]
  We propose new joint system-wise optimization techniques for the pipeline dialog system. First, we propose a new data augmentation approach which automates the labeling process for NLU training. Second, we propose a novel policy parameterization with Poisson distribution that enables better exploration and offers a way to compute policy gradient.
  arXiv  Detail & Related papers  (2021-06-09T06:44:57Z)

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.