Learning to explore when mistakes are not allowed

• URL: http://arxiv.org/abs/2502.13801v1
• Date: Wed, 19 Feb 2025 15:11:51 GMT
• Title: Learning to explore when mistakes are not allowed
• Authors: Charly Pecqueux-Guézénec, Stéphane Doncieux, Nicolas Perrin-Gilbert,
• Abstract summary: 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.
• Score: 1.179778723980276
• License:
• Abstract: Goal-Conditioned Reinforcement Learning (GCRL) provides a versatile framework for developing unified controllers capable of handling wide ranges of tasks, exploring environments, and adapting behaviors. However, its reliance on trial-and-error poses challenges for real-world applications, as errors can result in costly and potentially damaging consequences. To address the need for safer learning, 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, therefore a policy trained for safety without exploration purposes can still be exploited globally. Our proposed approach involves two distinct phases. First, during a pretraining phase, we employ safe reinforcement learning and distributional techniques to train a safety policy that actively tries to avoid failures in various situations. In the subsequent safe exploration phase, a goal-conditioned (GC) policy is learned while ensuring safety. To achieve this, we implement an action-selection mechanism leveraging the previously learned distributional safety critics to arbitrate between the safety policy and the GC policy, ensuring safe exploration by switching to the safety policy when needed. 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, in stark contrast to traditional GCRL approaches. Additionally, we conduct an ablation study and analyze failure modes, offering insights for future research directions.

Related papers

• RACER: Epistemic Risk-Sensitive RL Enables Fast Driving with Fewer Crashes [57.319845580050924]
  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.
  arXiv  Detail & Related papers  (2024-05-07T23:32:36Z)
• Safeguarded Progress in Reinforcement Learning: Safe Bayesian Exploration for Control Policy Synthesis [63.532413807686524]
  This paper addresses the problem of maintaining safety during training in Reinforcement Learning (RL) We propose a new architecture that handles the trade-off between efficient progress and safety during exploration.
  arXiv  Detail & Related papers  (2023-12-18T16:09:43Z)
• Probabilistic Counterexample Guidance for Safer Reinforcement Learning (Extended Version) [1.279257604152629]
  Safe exploration aims at addressing the limitations of Reinforcement Learning (RL) in safety-critical scenarios. Several methods exist to incorporate external knowledge or to use sensor data to limit the exploration of unsafe states. In this paper, we target the problem of safe exploration by guiding the training with counterexamples of the safety requirement.
  arXiv  Detail & Related papers  (2023-07-10T22:28:33Z)
• Safe Reinforcement Learning with Dead-Ends Avoidance and Recovery [13.333197887318168]
  Safety is one of the main challenges in applying reinforcement learning to realistic environmental tasks. We propose a method to construct a boundary that discriminates safe and unsafe states. Our approach has better task performance with less safety violations than state-of-the-art algorithms.
  arXiv  Detail & Related papers  (2023-06-24T12:02:50Z)
• MESA: Offline Meta-RL for Safe Adaptation and Fault Tolerance [73.3242641337305]
  Recent work learns risk measures which measure the probability of violating constraints, which can then be used to enable safety. We cast safe exploration as an offline meta-RL problem, where the objective is to leverage examples of safe and unsafe behavior across a range of environments. We then propose MEta-learning for Safe Adaptation (MESA), an approach for meta-learning Simulation a risk measure for safe RL.
  arXiv  Detail & Related papers  (2021-12-07T08:57:35Z)
• 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)
• 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)
• Provably Safe PAC-MDP Exploration Using Analogies [87.41775218021044]
  Key challenge in applying reinforcement learning to safety-critical domains is understanding how to balance exploration and safety. We propose Analogous Safe-state Exploration (ASE), an algorithm for provably safe exploration in MDPs with unknown, dynamics. Our method exploits analogies between state-action pairs to safely learn a near-optimal policy in a PAC-MDP sense.
  arXiv  Detail & Related papers  (2020-07-07T15:50:50Z)
• Safe reinforcement learning for probabilistic reachability and safety specifications: A Lyapunov-based approach [2.741266294612776]
  We propose a model-free safety specification method that learns the maximal probability of safe operation. Our approach constructs a Lyapunov function with respect to a safe policy to restrain each policy improvement stage. It yields a sequence of safe policies that determine the range of safe operation, called the safe set.
  arXiv  Detail & Related papers  (2020-02-24T09:20:03Z)

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.