Differential Assessment of Black-Box AI Agents

• URL: http://arxiv.org/abs/2203.13236v1
• Date: Thu, 24 Mar 2022 17:48:58 GMT
• Title: Differential Assessment of Black-Box AI Agents
• Authors: Rashmeet Kaur Nayyar, Pulkit Verma, Siddharth Srivastava
• Abstract summary: We propose a novel approach to differentially assess black-box AI agents that have drifted from their previously known models. We leverage sparse observations of the drifted agent's current behavior and knowledge of its initial model to generate an active querying policy. Empirical evaluation shows that our approach is much more efficient than re-learning the agent model from scratch.
• Score: 29.98710357871698
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Much of the research on learning symbolic models of AI agents focuses on agents with stationary models. This assumption fails to hold in settings where the agent's capabilities may change as a result of learning, adaptation, or other post-deployment modifications. Efficient assessment of agents in such settings is critical for learning the true capabilities of an AI system and for ensuring its safe usage. In this work, we propose a novel approach to differentially assess black-box AI agents that have drifted from their previously known models. As a starting point, we consider the fully observable and deterministic setting. We leverage sparse observations of the drifted agent's current behavior and knowledge of its initial model to generate an active querying policy that selectively queries the agent and computes an updated model of its functionality. Empirical evaluation shows that our approach is much more efficient than re-learning the agent model from scratch. We also show that the cost of differential assessment using our method is proportional to the amount of drift in the agent's functionality.

Related papers

• From Novice to Expert: LLM Agent Policy Optimization via Step-wise Reinforcement Learning [62.54484062185869]
  We introduce StepAgent, which utilizes step-wise reward to optimize the agent's reinforcement learning process. We propose implicit-reward and inverse reinforcement learning techniques to facilitate agent reflection and policy adjustment.
  arXiv  Detail & Related papers  (2024-11-06T10:35:11Z)
• Improving Agent Behaviors with RL Fine-tuning for Autonomous Driving [17.27549891731047]
  We improve the reliability of agent behaviors by closed-loop fine-tuning of behavior models with reinforcement learning. Our method demonstrates improved overall performance, as well as improved targeted metrics such as collision rate. We present a novel policy evaluation benchmark to directly assess the ability of simulated agents to measure the quality of autonomous vehicle planners.
  arXiv  Detail & Related papers  (2024-09-26T23:40:33Z)
• Dynamic Knowledge Injection for AIXI Agents [17.4429135205363]
  We introduce a new agent called DynamicHedgeAIXI that maintains an exact Bayesian mixture over dynamically changing sets of models. Experimental results on epidemic control on contact networks validates the agent's practical utility.
  arXiv  Detail & Related papers  (2023-12-18T13:34:17Z)
• QualEval: Qualitative Evaluation for Model Improvement [82.73561470966658]
  We propose QualEval, which augments quantitative scalar metrics with automated qualitative evaluation as a vehicle for model improvement. QualEval uses a powerful LLM reasoner and our novel flexible linear programming solver to generate human-readable insights. We demonstrate that leveraging its insights, for example, improves the absolute performance of the Llama 2 model by up to 15% points relative.
  arXiv  Detail & Related papers  (2023-11-06T00:21:44Z)
• Autonomous Capability Assessment of Sequential Decision-Making Systems in Stochastic Settings (Extended Version) [27.825419721676766]
  It is essential for users to understand what their AI systems can and can't do in order to use them safely. This paper presents a new approach for modeling the capabilities of black-box AI systems that can plan and act.
  arXiv  Detail & Related papers  (2023-06-07T22:05:48Z)
• MERMAIDE: Learning to Align Learners using Model-Based Meta-Learning [62.065503126104126]
  We study how a principal can efficiently and effectively intervene on the rewards of a previously unseen learning agent in order to induce desirable outcomes. This is relevant to many real-world settings like auctions or taxation, where the principal may not know the learning behavior nor the rewards of real people. We introduce MERMAIDE, a model-based meta-learning framework to train a principal that can quickly adapt to out-of-distribution agents.
  arXiv  Detail & Related papers  (2023-04-10T15:44:50Z)
• Explaining Reinforcement Learning Policies through Counterfactual Trajectories [147.7246109100945]
  A human developer must validate that an RL agent will perform well at test-time. Our method conveys how the agent performs under distribution shifts by showing the agent's behavior across a wider trajectory distribution. In a user study, we demonstrate that our method enables users to score better than baseline methods on one of two agent validation tasks.
  arXiv  Detail & Related papers  (2022-01-29T00:52:37Z)
• Sample-Efficient Reinforcement Learning via Conservative Model-Based Actor-Critic [67.00475077281212]
  Model-based reinforcement learning algorithms are more sample efficient than their model-free counterparts. We propose a novel approach that achieves high sample efficiency without the strong reliance on accurate learned models. We show that CMBAC significantly outperforms state-of-the-art approaches in terms of sample efficiency on several challenging tasks.
  arXiv  Detail & Related papers  (2021-12-16T15:33:11Z)
• Active Feature Acquisition with Generative Surrogate Models [11.655069211977464]
  In this work, we consider models that perform active feature acquisition (AFA) and query the environment for unobserved features. Our work reformulates the Markov decision process (MDP) that underlies the AFA problem as a generative modeling task. We propose learning a generative surrogate model ( GSM) that captures the dependencies among input features to assess potential information gain from acquisitions.
  arXiv  Detail & Related papers  (2020-10-06T02:10:06Z)
• On the model-based stochastic value gradient for continuous reinforcement learning [50.085645237597056]
  We show that simple model-based agents can outperform state-of-the-art model-free agents in terms of both sample-efficiency and final reward. Our findings suggest that model-based policy evaluation deserves closer attention.
  arXiv  Detail & Related papers  (2020-08-28T17:58:29Z)
• Agent Modelling under Partial Observability for Deep Reinforcement Learning [12.903487594031276]
  Existing methods for agent modelling assume knowledge of the local observations and chosen actions of the modelled agents during execution. We learn to extract representations about the modelled agents conditioned only on the local observations of the controlled agent. The representations are used to augment the controlled agent's decision policy which is trained via deep reinforcement learning.
  arXiv  Detail & Related papers  (2020-06-16T18:43:42Z)

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.