Efficient Reinforcement Learning for Autonomous Driving with Parameterized Skills and Priors

• URL: http://arxiv.org/abs/2305.04412v1
• Date: Mon, 8 May 2023 01:39:35 GMT
• Title: Efficient Reinforcement Learning for Autonomous Driving with Parameterized Skills and Priors
• Authors: Letian Wang, Jie Liu, Hao Shao, Wenshuo Wang, Ruobing Chen, Yu Liu, Steven L. Waslander
• Abstract summary: ASAP-RL is an efficient reinforcement learning algorithm for autonomous driving. A skill parameter inverse recovery method is proposed to convert expert demonstrations from control space to skill space. We validate our proposed method on interactive dense-traffic driving tasks given simple and sparse rewards.
• Score: 16.87227671645374
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: When autonomous vehicles are deployed on public roads, they will encounter countless and diverse driving situations. Many manually designed driving policies are difficult to scale to the real world. Fortunately, reinforcement learning has shown great success in many tasks by automatic trial and error. However, when it comes to autonomous driving in interactive dense traffic, RL agents either fail to learn reasonable performance or necessitate a large amount of data. Our insight is that when humans learn to drive, they will 1) make decisions over the high-level skill space instead of the low-level control space and 2) leverage expert prior knowledge rather than learning from scratch. Inspired by this, we propose ASAP-RL, an efficient reinforcement learning algorithm for autonomous driving that simultaneously leverages motion skills and expert priors. We first parameterized motion skills, which are diverse enough to cover various complex driving scenarios and situations. A skill parameter inverse recovery method is proposed to convert expert demonstrations from control space to skill space. A simple but effective double initialization technique is proposed to leverage expert priors while bypassing the issue of expert suboptimality and early performance degradation. We validate our proposed method on interactive dense-traffic driving tasks given simple and sparse rewards. Experimental results show that our method can lead to higher learning efficiency and better driving performance relative to previous methods that exploit skills and priors differently. Code is open-sourced to facilitate further research.

Related papers

• SPIRE: Synergistic Planning, Imitation, and Reinforcement Learning for Long-Horizon Manipulation [58.14969377419633]
  We propose spire, a system that decomposes tasks into smaller learning subproblems and second combines imitation and reinforcement learning to maximize their strengths. We find that spire outperforms prior approaches that integrate imitation learning, reinforcement learning, and planning by 35% to 50% in average task performance.
  arXiv  Detail & Related papers  (2024-10-23T17:42:07Z)
• Scaling Is All You Need: Autonomous Driving with JAX-Accelerated Reinforcement Learning [9.25541290397848]
  Reinforcement learning has been demonstrated to outperform even the best humans in complex domains like video games. We conduct large-scale reinforcement learning experiments for autonomous driving. Our best performing policy reduces the failure rate by 64% while improving the rate of driving progress by 25% compared to the policies produced by state-of-the-art machine learning for autonomous driving.
  arXiv  Detail & Related papers  (2023-12-23T00:07:06Z)
• A Language Agent for Autonomous Driving [31.359413767191608]
  We propose a paradigm shift to integrate human-like intelligence into autonomous driving systems. Our approach, termed Agent-Driver, transforms the traditional autonomous driving pipeline by introducing a versatile tool library. Powered by Large Language Models (LLMs), our Agent-Driver is endowed with intuitive common sense and robust reasoning capabilities.
  arXiv  Detail & Related papers  (2023-11-17T18:59:56Z)
• Rethinking Closed-loop Training for Autonomous Driving [82.61418945804544]
  We present the first empirical study which analyzes the effects of different training benchmark designs on the success of learning agents. We propose trajectory value learning (TRAVL), an RL-based driving agent that performs planning with multistep look-ahead. Our experiments show that TRAVL can learn much faster and produce safer maneuvers compared to all the baselines.
  arXiv  Detail & Related papers  (2023-06-27T17:58:39Z)
• Comprehensive Training and Evaluation on Deep Reinforcement Learning for Automated Driving in Various Simulated Driving Maneuvers [0.4241054493737716]
  This study implements, evaluating, and comparing the two DRL algorithms, Deep Q-networks (DQN) and Trust Region Policy Optimization (TRPO) Models trained on the designed ComplexRoads environment can adapt well to other driving maneuvers with promising overall performance.
  arXiv  Detail & Related papers  (2023-06-20T11:41:01Z)
• FastRLAP: A System for Learning High-Speed Driving via Deep RL and Autonomous Practicing [71.76084256567599]
  We present a system that enables an autonomous small-scale RC car to drive aggressively from visual observations using reinforcement learning (RL) Our system, FastRLAP (faster lap), trains autonomously in the real world, without human interventions, and without requiring any simulation or expert demonstrations. The resulting policies exhibit emergent aggressive driving skills, such as timing braking and acceleration around turns and avoiding areas which impede the robot's motion, approaching the performance of a human driver using a similar first-person interface over the course of training.
  arXiv  Detail & Related papers  (2023-04-19T17:33:47Z)
• Visual Exemplar Driven Task-Prompting for Unified Perception in Autonomous Driving [100.3848723827869]
  We present an effective multi-task framework, VE-Prompt, which introduces visual exemplars via task-specific prompting. Specifically, we generate visual exemplars based on bounding boxes and color-based markers, which provide accurate visual appearances of target categories. We bridge transformer-based encoders and convolutional layers for efficient and accurate unified perception in autonomous driving.
  arXiv  Detail & Related papers  (2023-03-03T08:54:06Z)
• Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarios [147.16925581385576]
  We show how imitation learning combined with reinforcement learning can substantially improve the safety and reliability of driving policies. We train a policy on over 100k miles of urban driving data, and measure its effectiveness in test scenarios grouped by different levels of collision likelihood.
  arXiv  Detail & Related papers  (2022-12-21T23:59:33Z)
• Accelerating Robotic Reinforcement Learning via Parameterized Action Primitives [92.0321404272942]
  Reinforcement learning can be used to build general-purpose robotic systems. However, training RL agents to solve robotics tasks still remains challenging. In this work, we manually specify a library of robot action primitives (RAPS), parameterized with arguments that are learned by an RL policy. We find that our simple change to the action interface substantially improves both the learning efficiency and task performance.
  arXiv  Detail & Related papers  (2021-10-28T17:59:30Z)
• Vision-Based Autonomous Car Racing Using Deep Imitative Reinforcement Learning [13.699336307578488]
  Deep imitative reinforcement learning approach (DIRL) achieves agile autonomous racing using visual inputs. We validate our algorithm both in a high-fidelity driving simulation and on a real-world 1/20-scale RC-car with limited onboard computation.
  arXiv  Detail & Related papers  (2021-07-18T00:00:48Z)
• Automated Lane Change Strategy using Proximal Policy Optimization-based Deep Reinforcement Learning [10.909595997847443]
  Lane-change maneuvers are commonly executed by drivers to follow a certain routing plan, overtake a slower vehicle, adapt to a merging lane ahead, etc. In this study, we propose an automated lane change strategy using proximal policy optimization-based deep reinforcement learning. The trained agent is able to learn a smooth, safe, and efficient driving policy to make lane-change decisions.
  arXiv  Detail & Related papers  (2020-02-07T08:43:34Z)

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.