Skip to content
Conference Open access

A Mixture of Domain Experts Framework for Autonomous Navigation via Deep Reinforcement Learning

Oct 2026 · International Conference on Information and Software Technologies · pp. 411-420 · 0 citations · 19 references

TL;DR

Long-horizon evaluations across in-distribution and held-out CARLA towns show that the proposed architecture outperforms monolithic and end-to-end MoE baselines, especially under multi-scenario and out-of-distribution conditions.

Abstract

Autonomous driving in urban environments requires policies that handle heterogeneous maneuvers without collapsing into a weak generalist. This paper presents a hierarchical Mixture of Domain Experts framework for deep reinforcement learning in CARLA. We first train Soft Actor-Critic specialists for distinct driving primitives, including intersections, curves, straight roads, and roundabouts. We then freeze these experts and train a gating policy to compose their actions through dense or sparse routing. This separation reduces task interference and enables online skill composition. Long-horizon evaluations across in-distribution and held-out CARLA towns show that the proposed architecture outperforms monolithic and end-to-end MoE baselines, especially under multi-scenario and out-of-distribution conditions.

Read PDF

Similar papers

#artificial intelligence Review Sep 2026

State Trace Rationale As Auxiliary Task in Reinforcement Learning

STRAT, an auxiliary task that trains deep reinforcement learning agents to predict a short textual trace of their own state, solves complex environments where standard RL fails outright, while compacting state representations and preventing rank collapse.

Muhammad Umair Nasir, Alex Vogt, Steven James et al. · 0 citations
#artificial intelligence Preprint Sep 2026

Imitation Learning for Autonomous Driving in CARLA

This work studies how much closed-loop driving competence a compact multimodal policy can acquire from offline demonstrations in the CARLA simulator, and reports offline metrics and distinguish measured results from qualitative closed-loop observations.

Jordy Kieto · 1 citation
#reinforcement learning Conference Sep 2026

A hierarchical reinforcement learning approach for robot navigation integrating LiDAR priors and the options framework

This method formalizes the navigation task as a semiMarkov decision process and constructs a two-layer decision architecture with collaboration between a high-level manager and a low-level worker with collaboration between a high-level manager and a low-level worker.

Qi-Ming Chen · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.