Safe Reinforcement Learning

82 papers with code • 0 benchmarks • 1 datasets

This task has no description! Would you like to contribute one?

Libraries

Use these libraries to find Safe Reinforcement Learning models and implementations

Transductive Active Learning with Application to Safe Bayesian Optimization

jonhue/transductive-active-learning ICML Workshop on Aligning Reinforcement Learning Experimentalists and Theorists 2024

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 region.

1
12 Jul 2024

Safe Reinforcement Learning in Black-Box Environments via Adaptive Shielding

team-daniel/advice 28 May 2024

Empowering safe exploration of reinforcement learning (RL) agents during training is a critical impediment towards deploying RL agents in many real-world scenarios.

0
28 May 2024

Feasibility Consistent Representation Learning for Safe Reinforcement Learning

czp16/fcsrl 20 May 2024

A key obstacle in this endeavor is the estimation of safety constraints, which is typically more difficult than estimating a reward metric due to the sparse nature of the constraint signals.

5
20 May 2024

Balance Reward and Safety Optimization for Safe Reinforcement Learning: A Perspective of Gradient Manipulation

pku-alignment/omnisafe 2 May 2024

Ensuring the safety of Reinforcement Learning (RL) is crucial for its deployment in real-world applications.

881
02 May 2024

From Representational Harms to Quality-of-Service Harms: A Case Study on Llama 2 Safety Safeguards

khaoulachehbouni/llama2safeguards 20 Mar 2024

Despite growing mitigation efforts to develop safety safeguards, such as supervised safety-oriented fine-tuning and leveraging safe reinforcement learning from human feedback, multiple concerns regarding the safety and ingrained biases in these models remain.

0
20 Mar 2024

Policy Bifurcation in Safe Reinforcement Learning

thuzouwenjun/mupo 19 Mar 2024

Safe reinforcement learning (RL) offers advanced solutions to constrained optimal control problems.

8
19 Mar 2024

Sampling-based Safe Reinforcement Learning for Nonlinear Dynamical Systems

sharma1256/cbf-constrained_ppo 6 Mar 2024

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.

4
06 Mar 2024

Leveraging Approximate Model-based Shielding for Probabilistic Safety Guarantees in Continuous Environments

sacktock/ambs 1 Feb 2024

Shielding is a popular technique for achieving safe reinforcement learning (RL).

1
01 Feb 2024

Off-Policy Primal-Dual Safe Reinforcement Learning

pku-alignment/omnisafe 26 Jan 2024

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.

881
26 Jan 2024

Stable and Safe Human-aligned Reinforcement Learning through Neural Ordinary Differential Equations

liqunzhao/a-barrier-lyapunov-actor-critic-reinforcement-learning-approach-for-safe-and-stable-control 23 Jan 2024

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 human-aligned tasks where human safety is paramount.

15
23 Jan 2024