Humans are not Boltzmann Distributions: Challenges and Opportunities for Modelling Human Feedback and Interaction in Reinforcement Learning

• URL: http://arxiv.org/abs/2206.13316v1
• Date: Mon, 27 Jun 2022 13:58:51 GMT
• Title: Humans are not Boltzmann Distributions: Challenges and Opportunities for Modelling Human Feedback and Interaction in Reinforcement Learning
• Authors: David Lindner and Mennatallah El-Assady
• Abstract summary: We argue that these models are too simplistic and that RL researchers need to develop more realistic human models to design and evaluate their algorithms. This paper calls for research from different disciplines to address key questions about how humans provide feedback to AIs and how we can build more robust human-in-the-loop RL systems.
• Score: 13.64577704565643
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reinforcement learning (RL) commonly assumes access to well-specified reward functions, which many practical applications do not provide. Instead, recently, more work has explored learning what to do from interacting with humans. So far, most of these approaches model humans as being (nosily) rational and, in particular, giving unbiased feedback. We argue that these models are too simplistic and that RL researchers need to develop more realistic human models to design and evaluate their algorithms. In particular, we argue that human models have to be personal, contextual, and dynamic. This paper calls for research from different disciplines to address key questions about how humans provide feedback to AIs and how we can build more robust human-in-the-loop RL systems.

Related papers

• Real-time Addressee Estimation: Deployment of a Deep-Learning Model on the iCub Robot [52.277579221741746]
  Addressee Estimation is a skill essential for social robots to interact smoothly with humans. Inspired by human perceptual skills, a deep-learning model for Addressee Estimation is designed, trained, and deployed on an iCub robot. The study presents the procedure of such implementation and the performance of the model deployed in real-time human-robot interaction.
  arXiv  Detail & Related papers  (2023-11-09T13:01:21Z)
• Few-Shot Preference Learning for Human-in-the-Loop RL [13.773589150740898]
  Motivated by the success of meta-learning, we pre-train preference models on prior task data and quickly adapt them for new tasks using only a handful of queries. We reduce the amount of online feedback needed to train manipulation policies in Meta-World by 20$times$, and demonstrate the effectiveness of our method on a real Franka Panda Robot.
  arXiv  Detail & Related papers  (2022-12-06T23:12:26Z)
• Optimal Behavior Prior: Data-Efficient Human Models for Improved Human-AI Collaboration [0.5524804393257919]
  We show that using optimal behavior as a prior for human models makes these models vastly more data-efficient. We also show that using these improved human models often leads to better human-AI collaboration performance.
  arXiv  Detail & Related papers  (2022-11-03T06:10:22Z)
• JECC: Commonsense Reasoning Tasks Derived from Interactive Fictions [75.42526766746515]
  We propose a new commonsense reasoning dataset based on human's Interactive Fiction (IF) gameplay walkthroughs. Our dataset focuses on the assessment of functional commonsense knowledge rules rather than factual knowledge. Experiments show that the introduced dataset is challenging to previous machine reading models as well as the new large language models.
  arXiv  Detail & Related papers  (2022-10-18T19:20:53Z)
• Cognitive Models as Simulators: The Case of Moral Decision-Making [9.024707986238392]
  In this work, we substantiate the idea of $textitcognitive models as simulators$, which is to have AI systems interact with, and collect feedback from, cognitive models instead of humans. Here, we leverage this idea in the context of moral decision-making, by having reinforcement learning agents learn about fairness through interacting with a cognitive model of the Ultimatum Game (UG) Our work suggests that using cognitive models as simulators of humans is an effective approach for training AI systems, presenting an important way for computational cognitive science to make contributions to AI.
  arXiv  Detail & Related papers  (2022-10-08T23:14:14Z)
• Reward Uncertainty for Exploration in Preference-based Reinforcement Learning [88.34958680436552]
  We present an exploration method specifically for preference-based reinforcement learning algorithms. Our main idea is to design an intrinsic reward by measuring the novelty based on learned reward. Our experiments show that exploration bonus from uncertainty in learned reward improves both feedback- and sample-efficiency of preference-based RL algorithms.
  arXiv  Detail & Related papers  (2022-05-24T23:22:10Z)
• Modeling Human Behavior Part I -- Learning and Belief Approaches [0.0]
  We focus on techniques which learn a model or policy of behavior through exploration and feedback. Next generation autonomous and adaptive systems will largely include AI agents and humans working together as teams.
  arXiv  Detail & Related papers  (2022-05-13T07:33:49Z)
• PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training [94.87393610927812]
  We present an off-policy, interactive reinforcement learning algorithm that capitalizes on the strengths of both feedback and off-policy learning. We demonstrate that our approach is capable of learning tasks of higher complexity than previously considered by human-in-the-loop methods.
  arXiv  Detail & Related papers  (2021-06-09T14:10:50Z)
• Humans learn too: Better Human-AI Interaction using Optimized Human Inputs [2.5991265608180396]
  Humans rely more and more on systems with AI components. The AI community typically treats human inputs as a given and optimize AI models only. In this work, human inputs are optimized for better interaction with an AI model while keeping the model fixed.
  arXiv  Detail & Related papers  (2020-09-19T16:30:37Z)
• Weak Human Preference Supervision For Deep Reinforcement Learning [48.03929962249475]
  The current reward learning from human preferences could be used to resolve complex reinforcement learning (RL) tasks without access to a reward function. We propose a weak human preference supervision framework, for which we developed a human preference scaling model. Our established human-demonstration estimator requires human feedback only for less than 0.01% of the agent's interactions with the environment.
  arXiv  Detail & Related papers  (2020-07-25T10:37:15Z)
• Machine Common Sense [77.34726150561087]
  Machine common sense remains a broad, potentially unbounded problem in artificial intelligence (AI) This article deals with the aspects of modeling commonsense reasoning focusing on such domain as interpersonal interactions.
  arXiv  Detail & Related papers  (2020-06-15T13:59:47Z)

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.