Episodic Memory For Learning Subjective-timescale Models

Abstract

In model-based learning, an agent's model is commonly defined over transitions between consecutive states of an environment even though planning often requires reasoning over multi-step timescales, with intermediate states either unnecessary, or worse, accumulating prediction error. In contrast, intelligent behaviour in biological organisms is characterised by the ability to plan over varying temporal scales depending on the context. Inspired by the recent works on human time perception, we devise a novel approach to learning a transition dynamics model, based on the sequences of episodic memories that define the agent's subjective timescale - over which it learns world dynamics and over which future planning is performed. We implement this in the framework of active inference and demonstrate that the resulting subjective-timescale model (STM) can systematically vary the temporal extent of its predictions while preserving the same computational efficiency. Additionally, we show that ST

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyzakharov2020episodic

Related papers

• Multi Time Scale World Models (2023)2.51
• Deep Reinforcement Learning With Time-scale Invariant Memory (2024)0.00
• Learning When To Act: Interval-aware Reinforcement Learning With Predictive Temporal Structure (2026)0.00
• Learning, Fast And Slow: A Goal-directed Memory-based Approach For Dynamic Environments (2023)0.00
• Non-stationary Policy Learning For Multi-timescale Multi-agent Reinforcement Learning (2023)5.24
• Beyond Sliding Windows: Learning To Manage Memory In Non-markovian Environments (2025)0.00
• Continual Learning Using World Models For Pseudo-rehearsal (2019)0.00
• Sequential Memory Improves Sample And Memory Efficiency In Episodic Control (2021)0.00