Learning from Mistakes: Rollout-Retrieval Lifelong Policy Learning for Autonomous Driving

• URL: http://arxiv.org/abs/2606.30537v1
• Date: Mon, 29 Jun 2026 16:37:50 GMT
• Title: Learning from Mistakes: Rollout-Retrieval Lifelong Policy Learning for Autonomous Driving
• Abstract summary: This paper studies autonomous driving policy improvement from a lifelong learning perspective.<n>We propose Rollout-Retrieval Lifelong Policy Learning (R$2$LPL), a policy learning framework that retrieves corrective targets from recoverable policy-induced mistakes.<n>We evaluate R$2$LPL on large-scale closed-loop nuPlan benchmarks.
• Score: 18.991437941136876
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Autonomous driving policies should be able to improve continually as deployment exposes them to increasingly diverse and long-tail traffic situations. However, most learning-based policies are trained or fine-tuned on expert demonstrations and then rely largely on generalization to handle challenging closed-loop scenarios, lacking an explicit mechanism to correct and retain the mistakes exposed in these scenarios. This paper studies autonomous driving policy improvement from a lifelong learning perspective: Can a pretrained policy improve continually by accumulating corrective knowledge derived from its own mistakes, while retaining previously acquired driving competence? To answer this question, we propose Rollout-Retrieval Lifelong Policy Learning (R$^2$LPL), a policy learning framework that retrieves corrective targets from recoverable policy-induced mistakes and retains the resulting knowledge through lifelong policy learning. R^2LPL addresses a key bottleneck in continual policy improvement: closed-loop mistakes reveal where the policy is weak, but do not directly specify what the policy should learn. By filtering recoverable mistake-related states and retrieving feasible corrective targets, R$^2$LPL turns sparse failure evidence into compact supervised knowledge for stable and sample-efficient policy improvement. We evaluate R$^2$LPL on large-scale closed-loop nuPlan benchmarks. With only a few rollout and continual-learning cycles, R$^2$LPL elevates a learning-based planner with moderate initial performance to state-of-the-art performance across the evaluated benchmarks, especially on the challenging and long-tail Test14-hard split. These results demonstrate the effectiveness of R$^2$LPL in converting recoverable closed-loop mistakes into corrective knowledge for sustained policy improvement.

Related papers

• PATS: Policy-Aware Training Scaffolding for Agentic Reinforcement Learning [8.197606162420145]
  We propose a policy-centric training paradigm that reframes skills as a dynamic training scaffold.<n>Our framework, PATS, converts rollout groups from the latest policy into evidence cards and uses task-specific evaluation to adjust the context used in subsequent rollouts.
  arXiv  Detail & Related papers  (2026-07-23T15:24:35Z)
• LLM-as-a-Tutor: Policy-Aware Prompt Adaptation for Non-Verifiable RL [64.4276583943816]
  Reinforcement learning for non-verifiable instruction relies on judges with prompt-specific rubrics as reward signals.<n>While recent methods adapt these rubrics to the evolving policy during training, the training prompts themselves remain static.<n>This static approach often results in a critical misalignment between prompt difficulty and policy capability, leaving the judge unable to recover a discriminative reward signal.
  arXiv  Detail & Related papers  (2026-07-05T17:05:13Z)
• FAR: Failure-Aware Retry for Test-Time Recovery and Continual Policy Improvement [10.94594187411586]
  Failure-Aware Retry (FAR) is a framework that enables robots to learn from previous failures at test time, adapt their behavior accordingly, and eventually complete the task autonomously.<n>FAR substantially improves success rates and robustness, with average gains of 17.6% over the standard diffusion policy in simulation and 11.7% in the real world.
  arXiv  Detail & Related papers  (2026-07-01T16:01:54Z)
• Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning [50.738952715864116]
  Expressive continuous control policies form the backbone of advances in scaling imitation learning for simulated and real robot control.<n>We propose QGF (Q-Guided Flow), an RL algorithm that performs policy optimization entirely at test time.<n> Empirically, QGF outperforms prior test-time RL methods on single-task and goal-conditioned offline RL benchmarks.
  arXiv  Detail & Related papers  (2026-06-09T16:45:57Z)
• Robust Regularized Policy Iteration under Transition Uncertainty [6.7431287237221085]
  We formulate offline RL as robust policy optimization, treating the transition kernel as a decision variable within an uncertainty set.<n>We propose Robust Regularized Policy Iteration (RRPI), which replaces the intractable max-min bilevel objective with a tractable KL-regularized surrogate.<n>Experiments on D4RL benchmarks demonstrate that RRPI achieves strong average performance, outperforming recent baselines.
  arXiv  Detail & Related papers  (2026-03-10T08:18:27Z)
• When to Act, Ask, or Learn: Uncertainty-Aware Policy Steering [10.01278648231868]
  Policy steering is an emerging way to adapt robot behaviors at deployment-time.<n> Vision-Language Models (VLMs) are promising general-purpose verifiers due to their reasoning capabilities.<n>We propose uncertainty-aware policy steering (UPS), a framework that jointly reasons about semantic task uncertainty and low-level action feasibility.
  arXiv  Detail & Related papers  (2026-02-25T23:23:22Z)
• A Step Back: Prefix Importance Ratio Stabilizes Policy Optimization [58.116300485427764]
  Reinforcement learning post-training can elicit reasoning behaviors in large language models.<n> token-level correction often leads to unstable training dynamics when the degree of off-policyness is large.<n>We propose a simple yet effective objective, Minimum Prefix Ratio (MinPRO)
  arXiv  Detail & Related papers  (2026-01-30T08:47:19Z)
• Improving Policy Exploitation in Online Reinforcement Learning with Instant Retrospect Action [10.983482150597913]
  Existing value-based online reinforcement learning (RL) algorithms suffer from slow policy exploitation due to ineffective exploration and delayed policy updates.<n>We propose an algorithm called Instant Retrospect Action (IRA) to address these challenges.<n>IRA can significantly improve the learning efficiency and final performance of online RL algorithms on eight MuJoCo continuous control tasks.
  arXiv  Detail & Related papers  (2026-01-27T15:43:02Z)
• Offline Reinforcement Learning with On-Policy Q-Function Regularization [57.09073809901382]
  We deal with the (potentially catastrophic) extrapolation error induced by the distribution shift between the history dataset and the desired policy. We propose two algorithms taking advantage of the estimated Q-function through regularizations, and demonstrate they exhibit strong performance on the D4RL benchmarks.
  arXiv  Detail & Related papers  (2023-07-25T21:38:08Z)
• Offline Reinforcement Learning with Implicit Q-Learning [85.62618088890787]
  Current offline reinforcement learning methods need to query the value of unseen actions during training to improve the policy. We propose an offline RL method that never needs to evaluate actions outside of the dataset. This method enables the learned policy to improve substantially over the best behavior in the data through generalization.
  arXiv  Detail & Related papers  (2021-10-12T17:05:05Z)
• Simplifying Deep Reinforcement Learning via Self-Supervision [51.2400839966489]
  Self-Supervised Reinforcement Learning (SSRL) is a simple algorithm that optimize policies with purely supervised losses. We show that SSRL is surprisingly competitive to contemporary algorithms with more stable performance and less running time.
  arXiv  Detail & Related papers  (2021-06-10T06:29:59Z)
• BRPO: Batch Residual Policy Optimization [79.53696635382592]
  In batch reinforcement learning, one often constrains a learned policy to be close to the behavior (data-generating) policy. We propose residual policies, where the allowable deviation of the learned policy is state-action-dependent. We derive a new for RL method, BRPO, which learns both the policy and allowable deviation that jointly maximize a lower bound on policy performance.
  arXiv  Detail & Related papers  (2020-02-08T01:59:33Z)

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.