SAFE-GIL: SAFEty Guided Imitation Learning

• URL: http://arxiv.org/abs/2404.05249v1
• Date: Mon, 8 Apr 2024 07:25:25 GMT
• Title: SAFE-GIL: SAFEty Guided Imitation Learning
• Authors: Yusuf Umut Ciftci, Zeyuan Feng, Somil Bansal,
• Abstract summary: Behavior cloning is a popular approach to Imitation Learning, in which a robot observes an expert supervisor and learns a control policy. However, behavior cloning suffers from the "compounding error" problem - the policy errors compound as it deviates from the expert demonstrations and might lead to catastrophic system failures. We propose SAFE-GIL, an off-policy behavior cloning method that guides the expert via adversarial disturbance during data collection.
• Score: 7.979892202477701
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Behavior Cloning is a popular approach to Imitation Learning, in which a robot observes an expert supervisor and learns a control policy. However, behavior cloning suffers from the "compounding error" problem - the policy errors compound as it deviates from the expert demonstrations and might lead to catastrophic system failures, limiting its use in safety-critical applications. On-policy data aggregation methods are able to address this issue at the cost of rolling out and repeated training of the imitation policy, which can be tedious and computationally prohibitive. We propose SAFE-GIL, an off-policy behavior cloning method that guides the expert via adversarial disturbance during data collection. The algorithm abstracts the imitation error as an adversarial disturbance in the system dynamics, injects it during data collection to expose the expert to safety critical states, and collects corrective actions. Our method biases training to more closely replicate expert behavior in safety-critical states and allows more variance in less critical states. We compare our method with several behavior cloning techniques and DAgger on autonomous navigation and autonomous taxiing tasks and show higher task success and safety, especially in low data regimes where the likelihood of error is higher, at a slight drop in the performance.

Related papers

• Learning to explore when mistakes are not allowed [1.179778723980276]
  We propose a method that enables agents to learn goal-conditioned behaviors that explore without the risk of making harmful mistakes. Exploration without risks can seem paradoxical, but environment dynamics are often uniform in space. We evaluate our method in simulated environments and demonstrate that it not only provides substantial coverage of the goal space but also reduces the occurrence of mistakes to a minimum.
  arXiv  Detail & Related papers  (2025-02-19T15:11:51Z)
• 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)
• Safe Deep Reinforcement Learning by Verifying Task-Level Properties [84.64203221849648]
  Cost functions are commonly employed in Safe Deep Reinforcement Learning (DRL) The cost is typically encoded as an indicator function due to the difficulty of quantifying the risk of policy decisions in the state space. In this paper, we investigate an alternative approach that uses domain knowledge to quantify the risk in the proximity of such states by defining a violation metric.
  arXiv  Detail & Related papers  (2023-02-20T15:24:06Z)
• Don't do it: Safer Reinforcement Learning With Rule-based Guidance [2.707154152696381]
  During training, reinforcement learning systems interact with the world without considering the safety of their actions. We propose a new safe epsilon-greedy algorithm that uses safety rules to override agents' actions if they are considered to be unsafe.
  arXiv  Detail & Related papers  (2022-12-28T13:42:56Z)
• Safe Reinforcement Learning using Data-Driven Predictive Control [0.5459797813771499]
  We propose a data-driven safety layer that acts as a filter for unsafe actions. The safety layer penalizes the RL agent if the proposed action is unsafe and replaces it with the closest safe one. In a simulation, we show that our method outperforms state-of-the-art safe RL methods on the robotics navigation problem.
  arXiv  Detail & Related papers  (2022-11-20T17:10:40Z)
• Verifying Learning-Based Robotic Navigation Systems [61.01217374879221]
  We show how modern verification engines can be used for effective model selection. Specifically, we use verification to detect and rule out policies that may demonstrate suboptimal behavior. Our work is the first to demonstrate the use of verification backends for recognizing suboptimal DRL policies in real-world robots.
  arXiv  Detail & Related papers  (2022-05-26T17:56:43Z)
• SAFER: Data-Efficient and Safe Reinforcement Learning via Skill Acquisition [59.94644674087599]
  We propose SAFEty skill pRiors (SAFER), an algorithm that accelerates policy learning on complex control tasks under safety constraints. Through principled training on an offline dataset, SAFER learns to extract safe primitive skills. In the inference stage, policies trained with SAFER learn to compose safe skills into successful policies.
  arXiv  Detail & Related papers  (2022-02-10T05:43:41Z)
• Learn Zero-Constraint-Violation Policy in Model-Free Constrained Reinforcement Learning [7.138691584246846]
  We propose the safe set actor-critic (SSAC) algorithm, which confines the policy update using safety-oriented energy functions. The safety index is designed to increase rapidly for potentially dangerous actions. We claim that we can learn the energy function in a model-free manner similar to learning a value function.
  arXiv  Detail & Related papers  (2021-11-25T07:24:30Z)
• Learning to be Safe: Deep RL with a Safety Critic [72.00568333130391]
  A natural first approach toward safe RL is to manually specify constraints on the policy's behavior. We propose to learn how to be safe in one set of tasks and environments, and then use that learned intuition to constrain future behaviors.
  arXiv  Detail & Related papers  (2020-10-27T20:53:20Z)
• 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)

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.