Learning When To Act: Interval-aware Reinforcement Learning With Predictive Temporal Structure

Abstract

Autonomous agents operating in continuous environments must decide not only what to do, but when to act. We introduce a lightweight adaptive temporal control system that learns the optimal interval between cognitive ticks from experience, replacing ad hoc biologically inspired timers with a principled learned policy. The policy state is augmented with a predictive hyperbolic spread signal (a "curvature signal" shorthand) derived from hyperbolic geometry: the mean pairwise Poincare distance among n sampled futures embedded in the Poincare ball. High spread indicates a branching, uncertain future and drives the agent to act sooner; low spread signals predictability and permits longer rest intervals. We further propose an interval-aware reward that explicitly penalises inefficiency relative to the chosen wait time, correcting a systematic credit-assignment failure of naive outcome-based rewards in timing problems. We additionally introduce a joint spatio-temporal embedding (ATCPG-ST) that

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keydigioia2026learning

Related papers

• Interval Timing In Deep Reinforcement Learning Agents (2019)0.00
• Model-based Reinforcement Learning For Control Under Time-varying Dynamics (2026)0.00
• Emergent Time-keeping Mechanisms In A Deep Reinforcement Learning Agent Performing An Interval Timing Task (2025)0.00
• Tempo Adaptation In Non-stationary Reinforcement Learning (2023)0.00
• Episodic Memory For Learning Subjective-timescale Models (2020)0.00
• Optimizing Attention And Cognitive Control Costs Using Temporally-layered Architectures (2023)2.26
• Deep Reinforcement Learning Of Marked Temporal Point Processes (2018)0.00
• Demystifying Reinforcement Learning In Time-varying Systems (2022)0.00