Model-based safe deep reinforcement learning via a constrained proximal policy optimization algorithm
AK Jayant, S Bhatnagar - Advances in Neural Information …, 2022 - proceedings.neurips.cc
During initial iterations of training in most Reinforcement Learning (RL) algorithms, agents
perform a significant number of random exploratory steps. In the real world, this can limit the …
perform a significant number of random exploratory steps. In the real world, this can limit the …
Learning barrier certificates: Towards safe reinforcement learning with zero training-time violations
Training-time safety violations have been a major concern when we deploy reinforcement
learning algorithms in the real world. This paper explores the possibility of safe RL …
learning algorithms in the real world. This paper explores the possibility of safe RL …
Autonomous driving based on approximate safe action
X Wang, J Zhang, D Hou… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Safety limits the application of traditional reinforcement learning (RL) methods to
autonomous driving. To address the challenge of safe exploration in autonomous driving …
autonomous driving. To address the challenge of safe exploration in autonomous driving …
Safe driving via expert guided policy optimization
When learning common skills like driving, beginners usually have domain experts standing
by to ensure the safety of the learning process. We formulate such learning scheme under …
by to ensure the safety of the learning process. We formulate such learning scheme under …
Efficient off-policy safe reinforcement learning using trust region conditional value at risk
This letter aims to solve a safe reinforcement learning (RL) problem with risk measure-based
constraints. As risk measures, such as conditional value at risk (CVaR), focus on the tail …
constraints. As risk measures, such as conditional value at risk (CVaR), focus on the tail …
Learning off-policy with online planning
Reinforcement learning (RL) in low-data and risk-sensitive domains requires performant and
flexible deployment policies that can readily incorporate constraints during deployment. One …
flexible deployment policies that can readily incorporate constraints during deployment. One …
On the feasibility guarantees of deep reinforcement learning solutions for distribution system operation
MM Hosseini, M Parvania - IEEE Transactions on Smart Grid, 2023 - ieeexplore.ieee.org
Deep reinforcement learning (DRL) has scored unprecedented success in finding near-
optimal solutions in high-dimensional stochastic problems, leading to its extensive use in …
optimal solutions in high-dimensional stochastic problems, leading to its extensive use in …
Improving safety in deep reinforcement learning using unsupervised action planning
One of the key challenges to deep reinforcement learning (deep RL) is to ensure safety at
both training and testing phases. In this work, we propose a novel technique of …
both training and testing phases. In this work, we propose a novel technique of …
Safe exploration by solving early terminated mdp
Safe exploration is crucial for the real-world application of reinforcement learning (RL).
Previous works consider the safe exploration problem as Constrained Markov Decision …
Previous works consider the safe exploration problem as Constrained Markov Decision …
Safe Reinforcement Learning on the Constraint Manifold: Theory and Applications
Integrating learning-based techniques, especially reinforcement learning, into robotics is
promising for solving complex problems in unstructured environments. However, most …
promising for solving complex problems in unstructured environments. However, most …