mlsanityData to 14 Oct 2026

Learning What Matters Now: A Dual-Critic Context-Aware RL Framework for Priority-Driven Information Gain

arXiv 2506.06786 ↗First posted 7 Jun 2025cs.AIcited by 0

On the map: Deep reinforcement learning methods → Deep RL algorithms and representations

Abstract (arXiv)

Autonomous systems operating in high-stakes search-and-rescue (SAR) missions must continuously gather mission-critical information while flexibly adapting to shifting operational priorities. We propose CA-MIQ (Context-Aware Max-Information Q-learning), a lightweight dual-critic reinforcement learning (RL) framework that dynamically adjusts its exploration strategy whenever mission priorities change. CA-MIQ pairs a standard extrinsic critic for task reward with an intrinsic critic that fuses state-novelty, information-location awareness, and real-time priority alignment. A built-in shift detector triggers transient exploration boosts and selective critic resets, allowing the agent to re-focus after a priority revision. In a simulated SAR grid-world, where experiments specifically test adaptation to changes in the priority order of information types the agent is expected to focus on, CA-MIQ achieves nearly four times higher mission-success rates than baselines after a single priority shift and more than three times better performance in multiple-shift scenarios, achieving 100% recovery while baseline methods fail to adapt. These results highlight CA-MIQ's effectiveness in any discrete environment with piecewise-stationary information-value distributions.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods. Builds on 19 of its 25 references that are in the map. First posted on arXiv 7 Jun 2025.

Builds on

19 of 25 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximization16 Dec

Other references · 18

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  3. 2017Curiosity-driven Exploration by Self-supervised Predictioncited by 1,194
  4. 2018Exploration by Random Network Distillationcited by 993
  5. 2016Unifying Count-Based Exploration and Intrinsic Motivationcited by 639
  6. 2015Contextual Markov Decision Processescited by 220
  7. 2014Learning to Optimize via Information-Directed Samplingcited by 168
  8. 2022Exploration in Deep Reinforcement Learning: A Surveycited by 166
  9. 2020Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learningcited by 98
  10. 2017Surprise-Based Intrinsic Motivation for Deep Reinforcement Learningcited by 83
  11. 2013Hidden Parameter Markov Decision Processes: A Semiparametric Regression Approach for Discovering Latent Task Parametrizationscited by 70
  12. 2017Boltzmann Exploration Done Rightcited by 69
6 more
  1. 2022Regret Bounds for Information-Directed Reinforcement Learningcited by 24
  2. 2022Reinforcement Learning in Presence of Discrete Markovian Context Evolutioncited by 9
  3. 2023Target Search and Navigation in Heterogeneous Robot Systems with Deep Reinforcement Learningcited by 7
  4. 2024Selective Exploration and Information Gathering in Search and Rescue Using Hierarchical Learning Guided by Natural Language Inputcited by 6
  5. 2024Deep Reinforcement Learning for Time-Critical Wilderness Search And Rescue Using Dronescited by 5
  6. 2022AdverSAR: Adversarial Search and Rescue via Multi-Agent Reinforcement Learningcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Rule-based High-Level Coaching for Goal-Conditioned Reinforcement Learning in Search-and-Rescue UAV Missions Under Limited-Simulation Training
  2. 2025CARoL: Context-aware Adaptation for Robot Learning
  3. 2024Enhancing Information Freshness: An AoI Optimized Markov Decision Process
  4. 2025When Motion Learns to Listen: Diffusion-Prior Lyapunov Actor-Critic Framework with LLM Guidance for Stable and Robust AUV Control in Underwater Tasks
  5. 2026Adapting the Behavior of Reinforcement Learning Agents to Changing Action Spaces and Reward Functions
  6. 2026VISTA: An Attention-Based Multi-Agent Reinforcement Learning Architecture for Space Situational Awareness Sensor Tasking
  7. 2026Multi-Agent LLMs for Adaptive Acquisition in Bayesian Optimization
  8. 2026Learning to Explore: Scaling Agentic Reasoning via Exploration-Aware Policy Optimization