mlsanityData to 14 Oct 2026

A Cognitive Framework for Autonomous Agents: Toward Human-Inspired Design

arXiv 2601.16648 ↗First posted 23 Jan 2026eess.SY cs.SYcited by 0

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

Abstract (arXiv)

This work introduces a human-inspired reinforcement learning (RL) architecture that integrates Pavlovian and instrumental processes to enhance decision-making in autonomous systems. While existing engineering solutions rely almost exclusively on instrumental learning, neuroscience shows that humans use Pavlovian associations to leverage predictive cues to bias behavior before outcomes occur. We translate this dual-system mechanism into a cue-guided RL framework in which radio-frequency (RF) stimuli act as conditioned (Pavlovian) cues that modulate action selection. The proposed architecture combines Pavlovian values with instrumental policy optimization, improving navigation efficiency and cooperative behavior in unknown, partially observable environments. Simulation results demonstrate that cue-driven agents adapt faster, achieving superior performance compared to traditional instrumental-solo agents. This work highlights the potential of human learning principles to reshape digital agents intelligence.

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 8 of its 48 references that are in the map. First posted on arXiv 23 Jan 2026.

Builds on

8 of 48 references.

References · 8

  1. 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,353
  2. 2018Learning Latent Dynamics for Planning from Pixelscited by 1,264
  3. 2019When to Trust Your Model: Model-Based Policy Optimizationcited by 773
  4. 2014Distributed Estimation with Information-Seeking Control in Agent Networkcited by 3
  5. 2024Double Actor-Critic with TD Error-Driven Regularization in Reinforcement Learningcited by 3
  6. 2020Dynamic Radar Network of UAVs: A Joint Navigation and Tracking Approachcited by 2
  7. 2021Networks of UAVs of Low-Complexity for Time-Critical Localizationcited by 2
  8. 2024A Deep-NN Beamforming Approach for Dual Function Radar-Communication THz UAVcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2016Discovering Latent States for Model Learning: Applying Sensorimotor Contingencies Theory and Predictive Processing to Model Context
  2. 2025Autotelic Reinforcement Learning: Exploring Intrinsic Motivations for Skill Acquisition in Open-Ended Environments
  3. 2025Illuminating the Three Dogmas of Reinforcement Learning under Evolutionary Light
  4. 2025CuES: A Curiosity-driven and Environment-grounded Synthesis Framework for Agentic RL
  5. 2022Improving Multimodal Interactive Agents with Reinforcement Learning from Human Feedback
  6. 2026OHP-RL: Online Human Preference as Guidance in Reinforcement Learning for Robot Manipulation
  7. 2020Action and Perception as Divergence Minimization
  8. 2024Ego-Foresight: Self-supervised Learning of Agent-Aware Representations for Improved RL