Browse State-of-the-Art › Safe Exploration
Safe Exploration
43 papers with code · 0 benchmarks · 0 datasets archive 2025-07-28
Safe Exploration is an approach to collect ground truth data by safely interacting with the environment.
Source: Chance-Constrained Trajectory Optimization for Safe Exploration and Learning of Nonlinear Systems
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.
Papers archive 2025-07-28
archive papers tagged: 135 · with a code link: 43 · where Syntology ran a sample: 12 (11 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (12 of 135 tagged: 11 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)
Page 1 of 2: papers 1 to 100 of 135, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
26 Jan 2018 6 repositories listed Syntology 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)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.
-
22 May 2021 3 repositories listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified (of 6 harvested samples) · 1 pointer-only (licence)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…
-
26 Sep 2021 2 repositories listedBased 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…
-
27 May 2020 2 repositories listedEnsuring 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…
-
27 Nov 2017 2 repositories listedWe present a suite of reinforcement learning environments illustrating various safety properties of intelligent agents.
-
4 Jun 2025 1 repository listedAutonomous driving promises significant advancements in mobility, road safety and traffic efficiency, yet reinforcement learning and imitation learning face safe-exploration and distribution-shift challenges.
-
8 Feb 2025 1 repository listed Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 5 harvested samples) · 4 pointer-only (licence)This work highlights the potential of integrating reinforcement learning to enhance the performance of VLA models for real-world robotic applications.
-
18 Sep 2024 1 repository listedSafety is one of the key issues preventing the deployment of reinforcement learning techniques in real-world robots.
-
22 Jul 2024 1 repository listedThe 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…
-
12 Jul 2024 1 repository listedWe 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…
-
28 May 2024 1 repository listedEmpowering safe exploration of reinforcement learning (RL) agents during training is a critical challenge towards their deployment in many real-world scenarios.
-
29 Jan 2024 1 repository listedWe use established methods for vision-based tracking and introduce a centralized DQN controller.
-
3 Nov 2023 1 repository listed Syntology official (archive's flag): 12 ran · 12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 1 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 14 harvested samples) · 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…
-
10 Jul 2023 1 repository listedWe demonstrate our method's effectiveness in reducing safety violations during online exploration in preliminary experiments by an average of 40.
-
24 Mar 2023 1 repository listedThis 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…
-
9 Dec 2022 1 repository listed Syntology official (archive's flag): 5 ran · 6 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified (of 9 harvested samples) · 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.
-
3 Nov 2022 1 repository listedWe 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.
-
30 Oct 2022 1 repository listedFirst, 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.
-
20 Oct 2022 1 repository listedDeep Reinforcement Learning (DRL) has demonstrated impressive results in domains such as games and robotics, where task formulations are well-defined.
-
14 Oct 2022 1 repository listed Syntology official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified (of 13 harvested samples) · 8 pointer-only (licence)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.
-
12 Oct 2022 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples) · 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.
-
30 Sep 2022 1 repository listedWe 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…
-
16 Sep 2022 1 repository listedNevertheless, several challenges hinder the practical adoption of DRL in commercial networks.
-
6 Jun 2022 1 repository listedWe further show that Simmer can stabilize training and improve the performance of safe RL with average constraints.
-
15 Feb 2022 1 repository listedAlthough 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…
-
24 Jan 2022 1 repository listedLearning optimal control policies directly on physical systems is challenging since even a single failure can lead to costly hardware damage.
-
1 Dec 2021 1 repository listedSafe reinforcement learning is extremely challenging--not only must the agent explore an unknown environment, it must do so while ensuring no safety constraint violations.
-
9 Nov 2021 1 repository listed Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 5 harvested samples) · 5 pointer-only (licence)Safe exploration is a key to applying reinforcement learning (RL) in safety-critical systems.
-
4 Nov 2021 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)Bayesian neural networks (BNNs) place distributions over the weights of a neural network to model uncertainty in the data and the network's prediction.
-
14 Apr 2021 1 repository listed Syntology 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 5 harvested samples) · 1 pointer-only (licence)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…
-
14 Oct 2020 1 repository listed
-
29 Sep 2020 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 3 unverified (of 3 harvested samples)
-
26 Sep 2020 1 repository listed
-
7 Jul 2020 1 repository listed
-
2 Jul 2020 1 repository listed
-
30 Jun 2020 1 repository listed
-
5 Jun 2020 1 repository listed
-
24 Feb 2020 1 repository listed
-
2 Feb 2020 1 repository listed
-
27 Jun 2019 1 repository listed
-
21 Jun 2016 1 repository listed
-
15 Jun 2016 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 2 unverified (of 2 harvested samples)
-
SLAC: Simulation-Pretrained Latent Action Space for Whole-Body Real-World RL4 Jun 2025 0 repositories listed
-
Bresa: Bio-inspired Reflexive Safe Reinforcement Learning for Contact-Rich Robotic Tasks27 Mar 2025 0 repositories listed
-
Safe exploration in reproducing kernel Hilbert spaces13 Mar 2025 0 repositories listed
-
Safety Representations for Safer Policy Learning27 Feb 2025 0 repositories listed
-
Learning to explore when mistakes are not allowed19 Feb 2025 0 repositories listed
-
Learning-Enhanced Safeguard Control for High-Relative-Degree Systems: Robust Optimization under Disturbances and Faults26 Jan 2025 0 repositories listed
-
Safe Bayesian Optimization for the Control of High-Dimensional Embodied Systems29 Dec 2024 0 repositories listed
-
ActSafe: Active Exploration with Safety Constraints for Reinforcement Learning12 Oct 2024 0 repositories listed
-
Robust Deep Reinforcement Learning for Volt-VAR Optimization in Active Distribution System under Uncertainty27 Sep 2024 0 repositories listed
-
Revisiting Safe Exploration in Safe Reinforcement learning2 Sep 2024 0 repositories listed
-
A Safe Self-evolution Algorithm for Autonomous Driving Based on Data-Driven Risk Quantification Model23 Aug 2024 0 repositories listed
-
Meta SAC-Lag: Towards Deployable Safe Reinforcement Learning via MetaGradient-based Hyperparameter Tuning15 Aug 2024 0 repositories listed
-
A Safe Exploration Strategy for Model-free Task Adaptation in Safety-constrained Grid Environments2 Aug 2024 0 repositories listed
-
Enhanced Safety in Autonomous Driving: Integrating Latent State Diffusion Model for End-to-End Navigation8 Jul 2024 0 repositories listed
-
5 Jun 2024 0 repositories listed Syntology 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 6 harvested samples) · 6 pointer-only (licence)
-
Preparing for Black Swans: The Antifragility Imperative for Machine Learning18 May 2024 0 repositories listed
-
Contextual Affordances for Safe Exploration in Robotic Scenarios10 May 2024 0 repositories listed
-
Safe Exploration Using Bayesian World Models and Log-Barrier Optimization9 May 2024 0 repositories listed
-
Information-Theoretic Safe Bayesian Optimization23 Feb 2024 0 repositories listed
-
Trajectory-wise Iterative Reinforcement Learning Framework for Auto-bidding23 Feb 2024 0 repositories listed
-
Towards Socially and Morally Aware RL agent: Reward Design With LLM23 Jan 2024 0 repositories listed
-
Towards Safe Load Balancing based on Control Barrier Functions and Deep Reinforcement Learning10 Jan 2024 0 repositories listed
-
Learning Human-like Representations to Enable Learning Human Values21 Dec 2023 0 repositories listed
-
Safe Exploration in Reinforcement Learning: Training Backup Control Barrier Functions with Zero Training Time Safety Violations13 Dec 2023 0 repositories listed
-
A safe exploration approach to constrained Markov decision processes1 Dec 2023 0 repositories listed
-
Safe Reinforcement Learning in a Simulated Robotic Arm28 Nov 2023 0 repositories listed
-
Safe Exploration in Reinforcement Learning: A Generalized Formulation and Algorithms5 Oct 2023 0 repositories listed
-
Reinforcement Learning by Guided Safe Exploration26 Jul 2023 0 repositories listed
-
Model-Assisted Probabilistic Safe Adaptive Control With Meta-Bayesian Learning3 Jul 2023 0 repositories listed
-
Safe Reinforcement Learning with Dead-Ends Avoidance and Recovery24 Jun 2023 0 repositories listed
-
Provably Learning Nash Policies in Constrained Markov Potential Games13 Jun 2023 0 repositories listed
-
Exploration of Unranked Items in Safe Online Learning to Re-Rank2 May 2023 0 repositories listed
-
System III: Learning with Domain Knowledge for Safety Constraints23 Apr 2023 0 repositories listed
-
Approximate Shielding of Atari Agents for Safe Exploration21 Apr 2023 0 repositories listed
-
A Human-Centered Safe Robot Reinforcement Learning Framework with Interactive Behaviors25 Feb 2023 0 repositories listed
-
Guiding Safe Exploration with Weakest Preconditions28 Sep 2022 0 repositories listed
-
Safe Reinforcement Learning of Dynamic High-Dimensional Robotic Tasks: Navigation, Manipulation, Interaction27 Sep 2022 0 repositories listed
-
Safe Reinforcement Learning with Contrastive Risk Prediction10 Sep 2022 0 repositories listed
-
Recursively Feasible Probabilistic Safe Online Learning with Control Barrier Functions23 Aug 2022 0 repositories listed
-
Sample-efficient Safe Learning for Online Nonlinear Control with Control Barrier Functions29 Jul 2022 0 repositories listed
-
Ablation Study of How Run Time Assurance Impacts the Training and Performance of Reinforcement Learning Agents8 Jul 2022 0 repositories listed
-
A Safe Semi-supervised Graph Convolution Network5 Jul 2022 0 repositories listed
-
Safe Exploration Incurs Nearly No Additional Sample Complexity for Reward-free RL28 Jun 2022 0 repositories listed
-
Learning to Drive Using Sparse Imitation Reinforcement Learning24 May 2022 0 repositories listed
-
Learn-to-Race Challenge 2022: Benchmarking Safe Learning and Cross-domain Generalisation in Autonomous Racing5 May 2022 0 repositories listed
-
Exploration in Deep Reinforcement Learning: A Survey2 May 2022 0 repositories listed
-
SCOPE: Safe Exploration for Dynamic Computer Systems Optimization22 Apr 2022 0 repositories listed
-
SAAC: Safe Reinforcement Learning as an Adversarial Game of Actor-Critics20 Apr 2022 0 repositories listed
-
Training and Evaluation of Deep Policies using Reinforcement Learning and Generative Models18 Apr 2022 0 repositories listed
-
Safe Reinforcement Learning via Shielding under Partial Observability2 Apr 2022 0 repositories listed
-
Safe Exploration for Efficient Policy Evaluation and Comparison26 Feb 2022 0 repositories listed
-
Model-Based Offline Meta-Reinforcement Learning with Regularization7 Feb 2022 0 repositories listed
-
Provably Efficient Primal-Dual Reinforcement Learning for CMDPs with Non-stationary Objectives and Constraints28 Jan 2022 0 repositories listed
-
MESA: Offline Meta-RL for Safe Adaptation and Fault Tolerance7 Dec 2021 0 repositories listed
-
DESTA: A Framework for Safe Reinforcement Learning with Markov Games of Intervention27 Oct 2021 0 repositories listed
-
Dual-Arm Adversarial Robot Learning15 Oct 2021 0 repositories listed
-
Safe Exploration in Linear Equality Constraint29 Sep 2021 0 repositories listed
Syntology lines on 14 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; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections