Safe Reinforcement Learning

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

1 dataset whose archive record lists this task, ordered by the archive's paper count.

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 100 papers with code (306 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.

• Constrained Policy Optimization
  30 May 2017 10 repositories listed Syntology ran 3 of 6 samples · 3 unverified · 3 pointer-only (licence)
  For many applications of reinforcement learning it can be more convenient to specify both a reward function and constraints, rather than trying to design behavior through the reward function.
• Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning
  13 Aug 2021 5 repositories listed
  The last half-decade has seen a steep rise in the number of contributions on safe learning methods for real-world robotic deployments from both the control and reinforcement learning communities.
• Balance Reward and Safety Optimization for Safe Reinforcement Learning: A Perspective of Gradient Manipulation
  2 May 2024 3 repositories listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  Ensuring the safety of Reinforcement Learning (RL) is crucial for its deployment in real-world applications.
• Datasets and Benchmarks for Offline Safe Reinforcement Learning
  15 Jun 2023 3 repositories listed Syntology ran 0 of 3 samples · 3 unverified
  This paper presents a comprehensive benchmarking suite tailored to offline safe reinforcement learning (RL) challenges, aiming to foster progress in the development and evaluation of safe learning algorithms in both the…
• Constrained Update Projection Approach to Safe Policy Optimization
  15 Sep 2022 3 repositories listed
  Compared to previous safe RL methods, CUP enjoys the benefits of 1) CUP generalizes the surrogate functions to generalized advantage estimator (GAE), leading to strong empirical performance.
• 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…
• Off-Policy Primal-Dual Safe Reinforcement Learning
  26 Jan 2024 2 repositories listed Syntology ran 13 of 22 samples · 9 unverified · 5 pointer-only (licence)
  Results on benchmark tasks show that our method not only achieves an asymptotic performance comparable to state-of-the-art on-policy methods while using much fewer samples, but also significantly reduces constraint…
• Stable and Safe Human-aligned Reinforcement Learning through Neural Ordinary Differential Equations
  23 Jan 2024 2 repositories listed
  Reinforcement learning (RL) excels in applications such as video games, but ensuring safety as well as the ability to achieve the specified goals remains challenging when using RL for real-world problems, such as…
• Self-Improving Safety Performance of Reinforcement Learning Based Driving with Black-Box Verification Algorithms
  29 Oct 2022 2 repositories listed
  In this work, we propose a self-improving artificial intelligence system to enhance the safety performance of reinforcement learning (RL)-based autonomous driving (AD) agents using black-box verification methods.
• Log Barriers for Safe Black-box Optimization with Application to Safe Reinforcement Learning
  21 Jul 2022 2 repositories listed Syntology ran 1 of 3 samples · 2 unverified
  We introduce a general approach for seeking a stationary point in high dimensional non-linear stochastic optimization problems in which maintaining safety during learning is crucial.
• Reachability Constrained Reinforcement Learning
  16 May 2022 2 repositories listed Syntology ran 4 of 5 samples · 1 unverified · 1 pointer-only (licence)
  Recent studies incorporate feasible sets into CRL with energy-based methods such as control barrier function (CBF), safety index (SI), and leverage prior conservative estimations of feasible sets, which harms the…
• Constrained Variational Policy Optimization for Safe Reinforcement Learning
  28 Jan 2022 2 repositories listed Syntology ran 5 of 11 samples · 6 unverified · 6 pointer-only (licence)
  Safe reinforcement learning (RL) aims to learn policies that satisfy certain constraints before deploying them to safety-critical applications.
• 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…
• Recovery RL: Safe Reinforcement Learning with Learned Recovery Zones
  29 Oct 2020 2 repositories listed Syntology ran 4 of 4 samples · 0 unverified
  Safety remains a central obstacle preventing widespread use of RL in the real world: learning new tasks in uncertain environments requires extensive exploration, but safety requires limiting exploration.
• Safe Reinforcement Learning with Scene Decomposition for Navigating Complex Urban Environments
  25 Apr 2019 2 repositories listed
  Navigating urban environments represents a complex task for automated vehicles.
• Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints
  9 Jun 2025 1 repository listed
  Existing approaches to language model alignment often treat safety as a tradeoff against helpfulness, which can lead to unacceptable responses in sensitive domains.
• Safe Multi-Agent Navigation guided by Goal-Conditioned Safe Reinforcement Learning
  25 Feb 2025 1 repository listed
  Utilizing this unified high-level graph and a shared low-level goal-conditioned safe RL policy, we extend this approach to address the multi-agent safe navigation problem.
• Risk-Averse Reinforcement Learning: An Optimal Transport Perspective on Temporal Difference Learning
  22 Feb 2025 1 repository listed
  The primary goal of reinforcement learning is to develop decision-making policies that prioritize optimal performance, frequently without considering risk or safety.
• Constraint-Adaptive Policy Switching for Offline Safe Reinforcement Learning
  25 Dec 2024 1 repository listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  Offline safe reinforcement learning (OSRL) involves learning a decision-making policy to maximize rewards from a fixed batch of training data to satisfy pre-defined safety constraints.
• Offline Safe Reinforcement Learning Using Trajectory Classification
  19 Dec 2024 1 repository listed Syntology ran 1 of 1 samples · 0 unverified
  In this paper, we propose to learn a policy that generates desirable trajectories and avoids undesirable trajectories.
• Tilted Quantile Gradient Updates for Quantile-Constrained Reinforcement Learning
  17 Dec 2024 1 repository listed
  Safe reinforcement learning (RL) is a popular and versatile paradigm to learn reward-maximizing policies with safety guarantees.
• Latent Safety-Constrained Policy Approach for Safe Offline Reinforcement Learning
  11 Dec 2024 1 repository listed Syntology ran 1 of 3 samples · 2 unverified · 3 pointer-only (licence)
  In safe offline reinforcement learning (RL), the objective is to develop a policy that maximizes cumulative rewards while strictly adhering to safety constraints, utilizing only offline data.
• Marvel: Accelerating Safe Online Reinforcement Learning with Finetuned Offline Policy
  5 Dec 2024 1 repository listed
  The high costs and risks involved in extensive environment interactions hinder the practical application of current online safe reinforcement learning (RL) methods.
• Think Smart, Act SMARL! Analyzing Probabilistic Logic Shields for Multi-Agent Reinforcement Learning
  7 Nov 2024 1 repository listed
  Safe reinforcement learning (RL) is crucial for real-world applications, and multi-agent interactions introduce additional safety challenges.
• 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.
• Real-world validation of safe reinforcement learning, model predictive control and decision tree-based home energy management systems
  14 Aug 2024 1 repository listed
  The results show that the simple rules, TreeC, and model predictive control-based methods achieved similar costs, with a difference of only 0.
• OASIS: Conditional Distribution Shaping for Offline Safe Reinforcement Learning
  19 Jul 2024 1 repository listed Syntology ran 4 of 8 samples · 4 unverified
  Offline safe reinforcement learning (RL) aims to train a policy that satisfies constraints using a pre-collected dataset.
• 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…
• CommonPower: A Framework for Safe Data-Driven Smart Grid Control
  5 Jun 2024 1 repository listed
  The growing complexity of power system management has led to an increased interest in reinforcement learning (RL).
• Enhancing Efficiency of Safe Reinforcement Learning via Sample Manipulation
  31 May 2024 1 repository listed
  Safe reinforcement learning (RL) is crucial for deploying RL agents in real-world applications, as it aims to maximize long-term rewards while satisfying safety constraints.

Syntology lines on 13 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.