# A Comprehensive Comparison of Reinforcement Learning Algorithms in Autonomous Driving

DevFeed: [A Comprehensive Comparison of Reinforcement Learning Algorithms in Autonomous Driving](<https://devfeed.tech/articles/a-comprehensive-comparison-of-reinforcement-learning-algorithms-in-autonomous-driving-123226.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.19429>)

Author: Dechen Xie, Mushuang Liu

Published: 2026-11-09T05:00:00Z

Content type: comparison

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Reinforcement learning](<https://devfeed.tech/topics/reinforcement-learning.md>), [autonomous vehicles](<https://devfeed.tech/topics/autonomous-vehicles.md>), [decision-making](<https://devfeed.tech/topics/decision-making.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [algorithm](<https://devfeed.tech/tags/algorithm.md>), [algorithms](<https://devfeed.tech/tags/algorithms.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [autonomous-driving](<https://devfeed.tech/tags/autonomous-driving.md>), [autonomous-vehicle](<https://devfeed.tech/tags/autonomous-vehicle.md>), [av](<https://devfeed.tech/tags/av.md>), [based](<https://devfeed.tech/tags/based.md>), [but](<https://devfeed.tech/tags/but.md>), [classification](<https://devfeed.tech/tags/classification.md>), [comparison](<https://devfeed.tech/tags/comparison.md>), [cost](<https://devfeed.tech/tags/cost.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-sy](<https://devfeed.tech/tags/cs-sy.md>), [data](<https://devfeed.tech/tags/data.md>), [decision-making](<https://devfeed.tech/tags/decision-making.md>), [deep](<https://devfeed.tech/tags/deep.md>), [driving](<https://devfeed.tech/tags/driving.md>), [eess-sy](<https://devfeed.tech/tags/eess-sy.md>), [learning](<https://devfeed.tech/tags/learning.md>), [learning-algorithms](<https://devfeed.tech/tags/learning-algorithms.md>), [reinforcement-learning](<https://devfeed.tech/tags/reinforcement-learning.md>)

## AI overview

The paper compares Fitted Value Iteration (FVI), Rollout Classification Policy Iteration (RCPI), Deep Q-Network (DQN), and discrete-action DDPG (D-DDPG) on the same autonomous-vehicle decision problem at an unsignalized intersection, assessing optimality, safety, training stability, and training and decision cost. The abstract reports that RCPI estimates the exact solution most closely and has the most stable training curve, but requires the most data. D-DDPG is the most data-efficient, with lower training stability. The supplied excerpt does not give detailed results for FVI or DQN.

## Source excerpt

arXiv:2610.19429v2 Announce Type: replace Abstract: This paper presents a comprehensive comparison of four representative Reinforcement Learning (RL) methods in autonomous vehicle (AV) decision-making, including Fitted Value Iteration (FVI), Rollout Classification Policy Iteration (RCPI), Deep Q-Network (DQN), and a discrete-action adaptation of Deep Deterministic Policy Gradient (D-DDPG). The four methods are applied to the same AV decision-making problem at an unsignalized intersection and are compared in terms of optimality, safety, training stability, and training and decision cost. Observations suggest that RCPI provides the closest estimation to the exact solution and has the most stable training curve; however, it is data-intensive and requires the largest volume of data. D-DDPG is the most data-efficient one, but at the price of the training stability. Based on the observations, we provide suggestions for the algorithm selection for AV decision making.