Action Space Reduction Strategies for Reinforcement Learning in Autonomous Driving

• URL: http://arxiv.org/abs/2507.05251v1
• Date: Mon, 07 Jul 2025 17:58:08 GMT
• Title: Action Space Reduction Strategies for Reinforcement Learning in Autonomous Driving
• Authors: Elahe Delavari, Feeza Khan Khanzada, Jaerock Kwon,
• Abstract summary: Reinforcement Learning (RL) offers a promising framework for autonomous driving.<n>Large and high-dimensional action spaces often used to support fine-grained control can impede training efficiency and increase exploration costs.<n>We introduce and evaluate two novel structured action space modification strategies for RL in autonomous driving.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement Learning (RL) offers a promising framework for autonomous driving by enabling agents to learn control policies through interaction with environments. However, large and high-dimensional action spaces often used to support fine-grained control can impede training efficiency and increase exploration costs. In this study, we introduce and evaluate two novel structured action space modification strategies for RL in autonomous driving: dynamic masking and relative action space reduction. These approaches are systematically compared against fixed reduction schemes and full action space baselines to assess their impact on policy learning and performance. Our framework leverages a multimodal Proximal Policy Optimization agent that processes both semantic image sequences and scalar vehicle states. The proposed dynamic and relative strategies incorporate real-time action masking based on context and state transitions, preserving action consistency while eliminating invalid or suboptimal choices. Through comprehensive experiments across diverse driving routes, we show that action space reduction significantly improves training stability and policy performance. The dynamic and relative schemes, in particular, achieve a favorable balance between learning speed, control precision, and generalization. These findings highlight the importance of context-aware action space design for scalable and reliable RL in autonomous driving tasks.

Related papers

• Multi-Timescale Hierarchical Reinforcement Learning for Unified Behavior and Control of Autonomous Driving [4.750705843012836]
  We propose a multi-timescale hierarchical reinforcement learning approach for autonomous driving.<n>High- and low-level RL policies are unified-trained to produce long-timescale motion guidance and short-timescale control commands.<n>Our approach significantly improves AD performance, effectively increasing driving efficiency, action consistency and safety.
  arXiv  Detail & Related papers  (2025-06-30T12:17:42Z)
• TeLL-Drive: Enhancing Autonomous Driving with Teacher LLM-Guided Deep Reinforcement Learning [61.33599727106222]
  TeLL-Drive is a hybrid framework that integrates a Teacher LLM to guide an attention-based Student DRL policy.<n>A self-attention mechanism then fuses these strategies with the DRL agent's exploration, accelerating policy convergence and boosting robustness.
  arXiv  Detail & Related papers  (2025-02-03T14:22:03Z)
• Hybrid Action Based Reinforcement Learning for Multi-Objective Compatible Autonomous Driving [9.39122455540358]
  Reinforcement Learning (RL) has shown excellent performance in solving decision-making and control problems of autonomous driving.<n>Driving is a multi-attribute problem, leading to challenges in achieving multi-objective compatibility for current RL methods.<n>We propose a Multi-objective Ensemble-Critic reinforcement learning method with Hybrid Parametrized Action for multi-objective compatible autonomous driving.
  arXiv  Detail & Related papers  (2025-01-14T13:10:13Z)
• From Imitation to Exploration: End-to-end Autonomous Driving based on World Model [24.578178308010912]
  RAMBLE is an end-to-end world model-based RL method for driving decision-making.<n>It can handle complex and dynamic traffic scenarios.<n>It achieves state-of-the-art performance in route completion rate on the CARLA Leaderboard 1.0 and completes all 38 scenarios on the CARLA Leaderboard 2.0.
  arXiv  Detail & Related papers  (2024-10-03T06:45:59Z)
• RACER: Epistemic Risk-Sensitive RL Enables Fast Driving with Fewer Crashes [57.319845580050924]
  We propose a reinforcement learning framework that combines risk-sensitive control with an adaptive action space curriculum. We show that our algorithm is capable of learning high-speed policies for a real-world off-road driving task.
  arXiv  Detail & Related papers  (2024-05-07T23:32:36Z)
• SAFE-SIM: Safety-Critical Closed-Loop Traffic Simulation with Diffusion-Controllable Adversaries [94.84458417662407]
  We introduce SAFE-SIM, a controllable closed-loop safety-critical simulation framework. Our approach yields two distinct advantages: 1) generating realistic long-tail safety-critical scenarios that closely reflect real-world conditions, and 2) providing controllable adversarial behavior for more comprehensive and interactive evaluations. We validate our framework empirically using the nuScenes and nuPlan datasets across multiple planners, demonstrating improvements in both realism and controllability.
  arXiv  Detail & Related papers  (2023-12-31T04:14:43Z)
• Robust Driving Policy Learning with Guided Meta Reinforcement Learning [49.860391298275616]
  We introduce an efficient method to train diverse driving policies for social vehicles as a single meta-policy. By randomizing the interaction-based reward functions of social vehicles, we can generate diverse objectives and efficiently train the meta-policy. We propose a training strategy to enhance the robustness of the ego vehicle's driving policy using the environment where social vehicles are controlled by the learned meta-policy.
  arXiv  Detail & Related papers  (2023-07-19T17:42:36Z)
• RLPG: Reinforcement Learning Approach for Dynamic Intra-Platoon Gap Adaptation for Highway On-Ramp Merging [14.540226579203207]
  A platoon refers to a group of vehicles traveling together in very close proximity. Recent research has revealed a detrimental effect of the extremely small intra-platoon gap on traffic flow for highway on-ramp merging. We present a novel reinforcement learning framework that adaptively adjusts the intra-platoon gap of an individual platoon member to maximize traffic flow.
  arXiv  Detail & Related papers  (2022-12-07T07:33:54Z)
• Unified Automatic Control of Vehicular Systems with Reinforcement Learning [64.63619662693068]
  This article contributes a streamlined methodology for vehicular microsimulation. It discovers high performance control strategies with minimal manual design. The study reveals numerous emergent behaviors resembling wave mitigation, traffic signaling, and ramp metering.
  arXiv  Detail & Related papers  (2022-07-30T16:23:45Z)
• Learning Interaction-aware Guidance Policies for Motion Planning in Dense Traffic Scenarios [8.484564880157148]
  This paper presents a novel framework for interaction-aware motion planning in dense traffic scenarios. We propose to learn, via deep Reinforcement Learning (RL), an interaction-aware policy providing global guidance about the cooperativeness of other vehicles. The learned policy can reason and guide the local optimization-based planner with interactive behavior to pro-actively merge in dense traffic while remaining safe in case the other vehicles do not yield.
  arXiv  Detail & Related papers  (2021-07-09T16:43:12Z)
• ReLMoGen: Leveraging Motion Generation in Reinforcement Learning for Mobile Manipulation [99.2543521972137]
  ReLMoGen is a framework that combines a learned policy to predict subgoals and a motion generator to plan and execute the motion needed to reach these subgoals. Our method is benchmarked on a diverse set of seven robotics tasks in photo-realistic simulation environments. ReLMoGen shows outstanding transferability between different motion generators at test time, indicating a great potential to transfer to real robots.
  arXiv  Detail & Related papers  (2020-08-18T08:05:15Z)
• Discrete Action On-Policy Learning with Action-Value Critic [72.20609919995086]
  Reinforcement learning (RL) in discrete action space is ubiquitous in real-world applications, but its complexity grows exponentially with the action-space dimension. We construct a critic to estimate action-value functions, apply it on correlated actions, and combine these critic estimated action values to control the variance of gradient estimation. These efforts result in a new discrete action on-policy RL algorithm that empirically outperforms related on-policy algorithms relying on variance control techniques.
  arXiv  Detail & Related papers  (2020-02-10T04:23:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.