# Dual-Gated Epistemic Time-Dilation: Autonomous Compute Modulation in Asynchronous MARL

arXiv: https://arxiv.org/abs/2603.23722 · HTML: https://mlsanity.com/paper/2603.23722/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 16 references that are in the map.
- First posted on arXiv 24 Mar 2026.

## Builds on (most cited first, 7 of 7)

- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [The StarCraft Multi-Agent Challenge](https://mlsanity.com/paper/1902.04043/) (2019)
- [Google Research Football: A Novel Reinforcement Learning Environment](https://mlsanity.com/paper/1907.11180/) (2019)
- [EGO-Planner: An ESDF-free Gradient-based Local Planner for Quadrotors](https://mlsanity.com/paper/2008.08835/) (2020)
- [Macro-Action-Based Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2004.08646/) (2020)
- [Asynchronous Credit Assignment for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2408.03692/) (2024)

## Abstract (arXiv)

While Multi-Agent Reinforcement Learning (MARL) algorithms achieve unprecedented successes across complex continuous domains, their standard deployment strictly adheres to a synchronous operational paradigm. Under this paradigm, agents are universally forced to execute deep neural network inferences at every micro-frame, regardless of immediate necessity. This dense throughput acts as a fundamental barrier to physical deployment on edge-devices where thermal and metabolic budgets are highly constrained. We propose Epistemic Time-Dilation MAPPO (ETD-MAPPO), augmented with a Dual-Gated Epistemic Trigger. Instead of depending on rigid frame-skipping (macro-actions), agents autonomously modulate their execution frequency by interpreting aleatoric uncertainty (via Shannon entropy of their policy) and epistemic uncertainty (via state-value divergence in a Twin-Critic architecture). To format this, we structure the environment as a Semi-Markov Decision Process (SMDP) and build the SMDP-Aligned Asynchronous Gradient Masking Critic to ensure proper credit assignment. Empirical findings demonstrate massive improvements (> 60% relative baseline acquisition leaps) over current temporal models. By assessing LBF, MPE, and the 115-dimensional state space of Google Research Football (GRF), ETD correctly prevented premature policy collapse. Remarkably, this unconstrained approach leads to emergent Temporal Role Specialization, reducing computational overhead by a statistically dominant 73.6% entirely during off-ball execution without deteriorating centralized task dominance.