RACER: Epistemic Risk-Sensitive RL Enables Fast Driving with Fewer Crashes

• URL: http://arxiv.org/abs/2405.04714v1
• Date: Tue, 7 May 2024 23:32:36 GMT
• Title: RACER: Epistemic Risk-Sensitive RL Enables Fast Driving with Fewer Crashes
• Authors: Kyle Stachowicz, Sergey Levine,
• Abstract summary: 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.
• Score: 57.319845580050924
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement learning provides an appealing framework for robotic control due to its ability to learn expressive policies purely through real-world interaction. However, this requires addressing real-world constraints and avoiding catastrophic failures during training, which might severely impede both learning progress and the performance of the final policy. In many robotics settings, this amounts to avoiding certain "unsafe" states. The high-speed off-road driving task represents a particularly challenging instantiation of this problem: a high-return policy should drive as aggressively and as quickly as possible, which often requires getting close to the edge of the set of "safe" states, and therefore places a particular burden on the method to avoid frequent failures. To both learn highly performant policies and avoid excessive failures, we propose a reinforcement learning framework that combines risk-sensitive control with an adaptive action space curriculum. Furthermore, we show that our risk-sensitive objective automatically avoids out-of-distribution states when equipped with an estimator for epistemic uncertainty. We implement our algorithm on a small-scale rally car and show that it is capable of learning high-speed policies for a real-world off-road driving task. We show that our method greatly reduces the number of safety violations during the training process, and actually leads to higher-performance policies in both driving and non-driving simulation environments with similar challenges.

Related papers

• Long and Short-Term Constraints Driven Safe Reinforcement Learning for Autonomous Driving [11.072917563013428]
  Reinforcement learning (RL) has been widely used in decision-making tasks, but it cannot guarantee the agent's safety in the training process. We propose a novel algorithm based on the long and short-term constraints (LSTC) for safe RL. We develop a safe RL method with dual-constraint optimization based on the Lagrange multiplier to optimize the training process for end-to-end autonomous driving.
  arXiv  Detail & Related papers  (2024-03-27T02:41:52Z)
• Evaluation of Safety Constraints in Autonomous Navigation with Deep Reinforcement Learning [62.997667081978825]
  We compare two learnable navigation policies: safe and unsafe. The safe policy takes the constraints into the account, while the other does not. We show that the safe policy is able to generate trajectories with more clearance (distance to the obstacles) and makes less collisions while training without sacrificing the overall performance.
  arXiv  Detail & Related papers  (2023-07-27T01:04:57Z)
• 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)
• Safety Correction from Baseline: Towards the Risk-aware Policy in Robotics via Dual-agent Reinforcement Learning [64.11013095004786]
  We propose a dual-agent safe reinforcement learning strategy consisting of a baseline and a safe agent. Such a decoupled framework enables high flexibility, data efficiency and risk-awareness for RL-based control. The proposed method outperforms the state-of-the-art safe RL algorithms on difficult robot locomotion and manipulation tasks.
  arXiv  Detail & Related papers  (2022-12-14T03:11:25Z)
• Automatically Learning Fallback Strategies with Model-Free Reinforcement Learning in Safety-Critical Driving Scenarios [9.761912672523977]
  We present a principled approach for a model-free Reinforcement Learning (RL) agent to capture multiple modes of behaviour in an environment. We introduce an extra pseudo-reward term to the reward model, to encourage exploration to areas of state-space different from areas privileged by the optimal policy. We show that we are able to learn useful policies that would have otherwise been missed out on during training, and unavailable to use when executing the control algorithm.
  arXiv  Detail & Related papers  (2022-04-11T15:34:49Z)
• Learning Barrier Certificates: Towards Safe Reinforcement Learning with Zero Training-time Violations [64.39401322671803]
  This paper explores the possibility of safe RL algorithms with zero training-time safety violations. We propose an algorithm, Co-trained Barrier Certificate for Safe RL (CRABS), which iteratively learns barrier certificates, dynamics models, and policies.
  arXiv  Detail & Related papers  (2021-08-04T04:59:05Z)
• Minimizing Safety Interference for Safe and Comfortable Automated Driving with Distributional Reinforcement Learning [3.923354711049903]
  We propose a distributional reinforcement learning framework to learn adaptive policies that can tune their level of conservativity at run-time based on the desired comfort and utility. We show that our algorithm learns policies that can still drive reliable when the perception noise is two times higher than the training configuration for automated merging and crossing at occluded intersections.
  arXiv  Detail & Related papers  (2021-07-15T13:36:55Z)
• Conservative Safety Critics for Exploration [120.73241848565449]
  We study the problem of safe exploration in reinforcement learning (RL) We learn a conservative safety estimate of environment states through a critic. We show that the proposed approach can achieve competitive task performance while incurring significantly lower catastrophic failure rates.
  arXiv  Detail & Related papers  (2020-10-27T17:54:25Z)
• Reinforcement Learning based Control of Imitative Policies for Near-Accident Driving [41.54021613421446]
  In near-accident scenarios, even a minor change in the vehicle's actions may result in drastically different consequences. We propose a hierarchical reinforcement and imitation learning (H-ReIL) approach that consists of low-level policies learned by IL for discrete driving modes, and a high-level policy learned by RL that switches between different driving modes.
  arXiv  Detail & Related papers  (2020-07-01T01:41:45Z)

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.