mlsanityData to 14 Oct 2026

Online Pareto-Optimal Decision-Making for Complex Tasks using Active Inference

arXiv 2406.11984 ↗First posted 17 Jun 2024cs.RO cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

When a robot autonomously performs a complex task, it frequently must balance competing objectives while maintaining safety. This becomes more difficult in uncertain environments with stochastic outcomes. Enhancing transparency in the robot's behavior and aligning with user preferences are also crucial. This paper introduces a novel framework for multi-objective reinforcement learning that ensures safe task execution, optimizes trade-offs between objectives, and adheres to user preferences. The framework has two main layers: a multi-objective task planner and a high-level selector. The planning layer generates a set of optimal trade-off plans that guarantee satisfaction of a temporal logic task. The selector uses active inference to decide which generated plan best complies with user preferences and aids learning. Operating iteratively, the framework updates a parameterized learning model based on collected data. Case studies and benchmarks on both manipulation and mobile robots show that our framework outperforms other methods and (i) learns multiple optimal trade-offs, (ii) adheres to a user preference, and (iii) allows the user to adjust the balance between (i) and (ii).

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 19 of its 67 references that are in the map. First posted on arXiv 17 Jun 2024.

Builds on

19 of 67 references.

References · 19

  1. 2016Variational Inference: A Review for Statisticianscited by 1,472
  2. 2018Soft Actor-Critic Algorithms and Applicationscited by 1,240
  3. 2018A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progresscited by 298
  4. 2021A Practical Guide to Multi-Objective Reinforcement Learning and Planningcited by 256
  5. 2017A Tutorial on Kernel Density Estimation and Recent Advancescited by 101
  6. 2018Dynamic Weights in Multi-Objective Deep Reinforcement Learningcited by 100
  7. 2020Deep active inference agents using Monte-Carlo methodscited by 72
  8. 2021Active Inference in Robotics and Artificial Agents: Survey and Challengescited by 52
  9. 2019Scaling active inferencecited by 30
  10. 2017Multi-objective Bandits: Optimizing the Generalized Gini Indexcited by 28
  11. 2022Designing Ecosystems of Intelligence from First Principlescited by 23
  12. 2018Multi-objective Contextual Bandit Problem with Similarity Informationcited by 21
7 more
  1. 2019Multi-Objective Generalized Linear Banditscited by 19
  2. 2023Optimal task and motion planning and execution for human-robot multi-agent systems in dynamic environmentscited by 8
  3. 2013Modeling Human Decision-making in Generalized Gaussian Multi-armed Banditscited by 7
  4. 2022Active Inference for Autonomous Decision-Making with Contextual Multi-Armed Banditscited by 6
  5. 2023Observation-Augmented Contextual Multi-Armed Bandits for Robotic Search and Explorationcited by 3
  6. 2023Optimal Cost-Preference Trade-off Planning with Multiple Temporal Taskscited by 2
  7. 2020Secure-by-Construction Optimal Path Planning for Linear Temporal Logic Taskscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024An Offline Adaptation Framework for Constrained Multi-Objective Reinforcement Learning
  2. 2026Learning specifications for reactive synthesis with safety constraints
  3. 2024Active Fine-Tuning of Multi-Task Policies
  4. 2018Human-in-the-Loop Mixed-Initiative Control under Temporal Tasks ↗
  5. 2022Planning to Practice: Efficient Online Fine-Tuning by Composing Goals in Latent Space
  6. 2026Distributional Active Inference
  7. 2024Demonstration-Enhanced Adaptable Multi-Objective Robot Navigation
  8. 2026RoboRouter: Training-Free Policy Routing for Robotic Manipulation