Safe Reinforcement Learning
76 papers with code • 0 benchmarks • 1 datasets
Benchmarks
These leaderboards are used to track progress in Safe Reinforcement Learning
Libraries
Use these libraries to find Safe Reinforcement Learning models and implementationsLatest papers
Policy Bifurcation in Safe Reinforcement Learning
Safe reinforcement learning (RL) offers advanced solutions to constrained optimal control problems.
Sampling-based Safe Reinforcement Learning for Nonlinear Dynamical Systems
We develop provably safe and convergent reinforcement learning (RL) algorithms for control of nonlinear dynamical systems, bridging the gap between the hard safety guarantees of control theory and the convergence guarantees of RL theory.
Leveraging Approximate Model-based Shielding for Probabilistic Safety Guarantees in Continuous Environments
Shielding is a popular technique for achieving safe reinforcement learning (RL).
Off-Policy Primal-Dual Safe Reinforcement Learning
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 violation during training.
NLBAC: A Neural Ordinary Differential Equations-based Framework for Stable and Safe Reinforcement Learning
Reinforcement learning (RL) excels in applications such as video games and robotics, but ensuring safety and stability remains challenging when using RL to control real-world systems where using model-free algorithms suffering from low sample efficiency might be prohibitive.
Safe reinforcement learning in uncertain contexts
In this work, we drop this assumption and show how we can perform safe learning when we cannot directly measure the context variables.
Imitate the Good and Avoid the Bad: An Incremental Approach to Safe Reinforcement Learning
In an exhaustive set of experiments, we demonstrate that our approach is able to outperform top benchmark approaches for solving Constrained RL problems, with respect to expected cost, CVaR cost, or even unknown cost constraints.
State-Wise Safe Reinforcement Learning With Pixel Observations
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 environments with contact-rich or non-smooth dynamics, and when dealing with high-dimensional pixel observations.
Hierarchical Framework for Interpretable and Probabilistic Model-Based Safe Reinforcement Learning
Deep reinforcement learning has been the pioneer for solving this problem without the need for relying on the physical model of complex systems by just interacting with it.
Safe RLHF: Safe Reinforcement Learning from Human Feedback
However, the inherent tension between the objectives of helpfulness and harmlessness presents a significant challenge during LLM training.