Safemil: Learning Offline Safe Imitation Policy From Non-preferred Trajectories

Abstract

In this work, we study the problem of offline safe imitation learning (IL). In many real-world settings, online interactions can be risky, and accurately specifying the reward and the safety cost information at each timestep can be difficult. However, it is often feasible to collect trajectories reflecting undesirable or risky behavior, implicitly conveying the behavior the agent should avoid. We refer to these trajectories as non-preferred trajectories. Unlike standard IL, which aims to mimic demonstrations, our agent must also learn to avoid risky behavior using non-preferred trajectories. In this paper, we propose a novel approach, SafeMIL, to learn a parameterized cost that predicts if the state-action pair is risky via Multiple Instance Learning. The learned cost is then used to avoid non-preferred behaviors, resulting in a policy that prioritizes safety. We empirically demonstrate that our approach can learn a safer policy that satisfies cost constraints without degrading the rew

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyburnwal2025safemil

Related papers

• Offline Safe Reinforcement Learning Using Trajectory Classification (2024)0.00
• Mitigating Covariate Shift In Imitation Learning Via Offline Data Without Great Coverage (2021)0.00
• Imitate The Good And Avoid The Bad: An Incremental Approach To Safe Reinforcement Learning (2023)0.00
• A Simple Solution For Offline Imitation From Observations And Examples With Possibly Incomplete Trajectories (2023)0.00
• Towards Fast Safe Online Reinforcement Learning Via Policy Finetuning (2024)0.00
• Learning From Good Trajectories In Offline Multi-agent Reinforcement Learning (2022)5.24
• Offline Imitation Learning By Controlling The Effective Planning Horizon (2024)0.00
• Constraints Penalized Q-learning For Safe Offline Reinforcement Learning (2021)0.00