Safe Exploration

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

No benchmark for this task in the archive.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

No dataset record in the archive lists this task.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Most implemented papers archive 2025-07-28

30 shown of 43 papers with code (135 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Safe Exploration in Continuous Action Spaces
  26 Jan 2018 6 repositories listed Syntology ran 1 of 1 samples · 0 unverified
  We address the problem of deploying a reinforcement learning (RL) agent on a physical system such as a datacenter cooling unit or robot, where critical constraints must never be violated.
• Feasible Actor-Critic: Constrained Reinforcement Learning for Ensuring Statewise Safety
  22 May 2021 3 repositories listed Syntology ran 1 of 6 samples · 5 unverified
  The safety constraints commonly used by existing safe reinforcement learning (RL) methods are defined only on expectation of initial states, but allow each certain state to be unsafe, which is unsatisfying for…
• MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning
  26 Sep 2021 2 repositories listed
  Based on MetaDrive, we construct a variety of RL tasks and baselines in both single-agent and multi-agent settings, including benchmarking generalizability across unseen scenes, safe exploration, and learning…
• SafeML: Safety Monitoring of Machine Learning Classifiers through Statistical Difference Measure
  27 May 2020 2 repositories listed
  Ensuring safety and explainability of machine learning (ML) is a topic of increasing relevance as data-driven applications venture into safety-critical application domains, traditionally committed to high safety…
• AI Safety Gridworlds
  27 Nov 2017 2 repositories listed
  We present a suite of reinforcement learning environments illustrating various safety properties of intelligent agents.
• Confidence-Guided Human-AI Collaboration: Reinforcement Learning with Distributional Proxy Value Propagation for Autonomous Driving
  4 Jun 2025 1 repository listed
  Autonomous driving promises significant advancements in mobility, road safety and traffic efficiency, yet reinforcement learning and imitation learning face safe-exploration and distribution-shift challenges.
• ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policy
  8 Feb 2025 1 repository listed Syntology ran 3 of 5 samples · 2 unverified
  This work highlights the potential of integrating reinforcement learning to enhance the performance of VLA models for real-world robotic applications.
• Handling Long-Term Safety and Uncertainty in Safe Reinforcement Learning
  18 Sep 2024 1 repository listed
  Safety is one of the key issues preventing the deployment of reinforcement learning techniques in real-world robots.
• Exterior Penalty Policy Optimization with Penalty Metric Network under Constraints
  22 Jul 2024 1 repository listed
  The penalty function method has recently been studied as an effective approach for handling constraints, which imposes constraints penalties on the objective to transform the constrained problem into an unconstrained…
• Transductive Active Learning with Application to Safe Bayesian Optimization
  12 Jul 2024 1 repository listed
  We analyze Safe BO under the lens of a generalization of active learning with concrete prediction targets where sampling is restricted to an accessible region of the domain, while prediction targets may lie outside this…
• Safe Reinforcement Learning in Black-Box Environments via Adaptive Shielding
  28 May 2024 1 repository listed
  Empowering safe exploration of reinforcement learning (RL) agents during training is a critical challenge towards their deployment in many real-world scenarios.
• A comparison of RL-based and PID controllers for 6-DOF swimming robots: hybrid underwater object tracking
  29 Jan 2024 1 repository listed
  We use established methods for vision-based tracking and introduce a centralized DQN controller.
• State-Wise Safe Reinforcement Learning With Pixel Observations
  3 Nov 2023 1 repository listed Syntology ran 12 of 14 samples · 2 unverified · 14 pointer-only (licence)
  In the context of safe exploration, Reinforcement Learning (RL) has long grappled with the challenges of balancing the tradeoff between maximizing rewards and minimizing safety violations, particularly in complex…
• Probabilistic Counterexample Guidance for Safer Reinforcement Learning (Extended Version)
  10 Jul 2023 1 repository listed
  We demonstrate our method's effectiveness in reducing safety violations during online exploration in preliminary experiments by an average of 40.
• Safe and Sample-efficient Reinforcement Learning for Clustered Dynamic Environments
  24 Mar 2023 1 repository listed
  This study proposes a safe and sample-efficient reinforcement learning (RL) framework to address two major challenges in developing applicable RL algorithms: satisfying safety constraints and efficiently learning with…
• Information-Theoretic Safe Exploration with Gaussian Processes
  9 Dec 2022 1 repository listed Syntology ran 5 of 9 samples · 4 unverified · 8 pointer-only (licence)
  We consider a sequential decision making task where we are not allowed to evaluate parameters that violate an a priori unknown (safety) constraint.
• Benefits of Monotonicity in Safe Exploration with Gaussian Processes
  3 Nov 2022 1 repository listed
  We consider the problem of sequentially maximising an unknown function over a set of actions while ensuring that every sampled point has a function value below a given safety threshold.
• Atlas: Automate Online Service Configuration in Network Slicing
  30 Oct 2022 1 repository listed
  First, we design a learning-based simulator to reduce the sim-to-real discrepancy, which is accomplished by a new parameter searching method based on Bayesian optimization.
• The Pump Scheduling Problem: A Real-World Scenario for Reinforcement Learning
  20 Oct 2022 1 repository listed
  Deep Reinforcement Learning (DRL) has demonstrated impressive results in domains such as games and robotics, where task formulations are well-defined.
• Model-based Safe Deep Reinforcement Learning via a Constrained Proximal Policy Optimization Algorithm
  14 Oct 2022 1 repository listed Syntology ran 5 of 13 samples · 8 unverified
  We compare our approach with relevant model-free and model-based approaches in Constrained RL using the challenging Safe Reinforcement Learning benchmark - the Open AI Safety Gym.
• Near-Optimal Multi-Agent Learning for Safe Coverage Control
  12 Oct 2022 1 repository listed Syntology ran 2 of 3 samples · 1 unverified · 3 pointer-only (licence)
  In this paper, we aim to efficiently learn the density to approximately solve the coverage problem while preserving the agents' safety.
• Safe Exploration Method for Reinforcement Learning under Existence of Disturbance
  30 Sep 2022 1 repository listed
  We define the safety during learning as satisfaction of the constraint conditions explicitly defined in terms of the state and propose a safe exploration method that uses partial prior knowledge of a controlled object…
• Toward Safe and Accelerated Deep Reinforcement Learning for Next-Generation Wireless Networks
  16 Sep 2022 1 repository listed
  Nevertheless, several challenges hinder the practical adoption of DRL in commercial networks.
• Effects of Safety State Augmentation on Safe Exploration
  6 Jun 2022 1 repository listed
  We further show that Simmer can stabilize training and improve the performance of safe RL with average constraints.
• CUP: A Conservative Update Policy Algorithm for Safe Reinforcement Learning
  15 Feb 2022 1 repository listed
  Although using bounds as surrogate functions to design safe RL algorithms have appeared in some existing works, we develop them at least three aspects: (i) We provide a rigorous theoretical analysis to extend the…
• GoSafeOpt: Scalable Safe Exploration for Global Optimization of Dynamical Systems
  24 Jan 2022 1 repository listed
  Learning optimal control policies directly on physical systems is challenging since even a single failure can lead to costly hardware damage.
• DOPE: Doubly Optimistic and Pessimistic Exploration for Safe Reinforcement Learning
  1 Dec 2021 1 repository listed
  Safe reinforcement learning is extremely challenging--not only must the agent explore an unknown environment, it must do so while ensuring no safety constraint violations.
• Safe Policy Optimization with Local Generalized Linear Function Approximations
  9 Nov 2021 1 repository listed Syntology ran 0 of 5 samples · 5 unverified · 5 pointer-only (licence)
  Safe exploration is a key to applying reinforcement learning (RL) in safety-critical systems.
• Infinite Time Horizon Safety of Bayesian Neural Networks
  4 Nov 2021 1 repository listed Syntology ran 2 of 2 samples · 0 unverified
  Bayesian neural networks (BNNs) place distributions over the weights of a neural network to model uncertainty in the data and the network's prediction.
• Safe Continuous Control with Constrained Model-Based Policy Optimization
  14 Apr 2021 1 repository listed Syntology ran 1 of 5 samples · 4 unverified
  Further, we provide theoretical and empirical analyses regarding the implications of model-usage on constrained policy optimization problems and introduce a practical algorithm that accelerates policy search with…

Syntology lines on 10 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.