Results 31 to 40 of about 7,404,725 (288)
Safe Reinforcement Learning With Model Uncertainty Estimates [PDF]
2019 International Conference on Robotics and Automation (ICRA), 2019 Many current autonomous systems are being designed with a strong reliance on black box predictions from deep neural networks (DNNs). However, DNNs tend to be overconfident in predictions on unseen data and can give unpredictable results for far-from-distribution test data.
Lutjens, Bjorn +2 more
openaire +4 more sources
Imagine to Ensure Safety in Hierarchical Reinforcement Learning
Machine Learning and Knowledge ExtractionThis work investigates the safe exploration problem in reinforcement learning, where an agent must maximize cumulative performance while simultaneously satisfying safety constraints.
Gregory Gorbov +2 more
doaj +1 more source
Agriculture, 2023 Due to the complex coupling of greenhouse environments, a number of challenges have been encountered in the research of automatic control in Venlo greenhouses.
Lihan Chen, Lihong Xu, Ruihua Wei
doaj +1 more source
Enhancing Safe Exploration Through Subgoal Guidance
TechnologiesReinforcement learning is a widely used approach for autonomous navigation, but it often struggles to reach distant, long-horizon goals under safety constraints. The primary reason for this suboptimal performance is that safety requirements significantly
Gregory Gorbov, Aleksandr Panov
doaj +1 more source
Safe Reinforcement Learning through Meta-learned Instincts [PDF]
The 2020 Conference on Artificial Life, 2020 An important goal in reinforcement learning is to create agents that can quickly adapt to new goals while avoiding situations that might cause damage to themselves or their environments. One way agents learn is through exploration mechanisms, which are needed to discover new policies.
Grbic, Djordje, Risi, Sebastian
openaire +3 more sources
Safe In-Context Reinforcement Learning
CoRRIn-context reinforcement learning (ICRL) is an emerging RL paradigm where an agent, after pretraining, can adapt to out-of-distribution test tasks without any parameter updates, instead relying on an expanding context of interaction history. While ICRL has shown impressive generalization, safety during this adaptation process remains unexplored ...
Amir Moeini +6 more
openaire +3 more sources
Probabilistic Policy Reuse for Safe Reinforcement Learning [PDF]
ACM Transactions on Autonomous and Adaptive Systems, 2018 This work introduces Policy Reuse for Safe Reinforcement Learning , an algorithm that combines Probabilistic Policy Reuse and teacher advice for safe exploration in dangerous and continuous state and action reinforcement learning problems in which the dynamic behavior is reasonably smooth and the space is Euclidean.
Javier García 0001 +1 more
openaire +3 more sources
Safe Reinforcement Learning via Episodic Control
IEEE AccessSafe reinforcement learning (Safe RL) aims to learn policies capable of learning and adapting within complex environments while ensuring actions remain free from catastrophic consequences.
Zhuo Li, Derui Zhu, Jens Grossklags
doaj +1 more source
Anytime Safe Reinforcement Learning
CoRRThis paper considers the problem of solving constrained reinforcement learning problems with anytime guarantees, meaning that the algorithmic solution returns a safe policy regardless of when it is terminated. Drawing inspiration from anytime constrained optimization, we introduce Reinforcement Learning-based Safe Gradient Flow (RL-SGF), an on ...
Pol Mestres +2 more
openaire +3 more sources
Balanced Domain Randomization for Safe Reinforcement Learning
Applied SciencesReinforcement Learning (RL) has enabled autonomous agents to achieve superhuman performance in diverse domains, including games, navigation, and robotic control.
Cheongwoong Kang +2 more
doaj +1 more source