Add to ORKGAbstract. In this paper we improve learning performance of a risk-aware robot facing navigation tasks by employing transfer learning; that is, we use information from a previously solved task to accelerate learn-ing in a new task. To do so, we transfer risk-aware memoryless stochas-tic abstract policies into a new task. We show how to incorporate risk-awareness into robotic navigation tasks, in particular when tasks are modeled as stochastic shortest path problems. We then show how to use a modified policy iteration algorithm, called AbsProb-PI, to obtain risk-neutral and risk-prone memoryless stochastic abstract policies. Finally, we propose a method that combines abstract policies, and show how to use the combined policy in a new navigati...
Abstract — Task learning in robotics is a time-consuming process, and model-based reinforcement lear...
A central goal of the robotics community is to develop general optimization algorithms for producing...
Model-free reinforcement learning has recently been shown to be effective at learning navigation pol...
In this paper we improve learning performance of a risk-aware robot facing navigation tasks by emplo...
Abstract—Reinforcement learning enables an agent to learn behavior by acquiring experience through t...
A maioria das propostas de planejamento de rotas para robôs móveis não leva em conta a existência de...
Formal methods based on the Markov decision process formalism, such as probabilistic computation tre...
Applying deep reinforcement learning to physical systems, as opposed to learning in simulation, pres...
In the real world, robots operate with imperfect sensors providing uncertain and incomplete informat...
Task learning in robotics requires repeatedly executing the same actions in different states to lear...
In my presentation I will present my research study which investigates artificial intelligence techn...
Abstract — We present a learning system which is able to quickly and reliably acquire a robust feedb...
In order for human-assisting robots to be deployed in the real world such as household environments,...
PhD thesisIn this thesis, we argue that autonomous robots operating in hostile and uncertain environ...
Keeping risk under control is a primary objective in many critical real-world domains, including fin...
Abstract — Task learning in robotics is a time-consuming process, and model-based reinforcement lear...
A central goal of the robotics community is to develop general optimization algorithms for producing...
Model-free reinforcement learning has recently been shown to be effective at learning navigation pol...
In this paper we improve learning performance of a risk-aware robot facing navigation tasks by emplo...
Abstract—Reinforcement learning enables an agent to learn behavior by acquiring experience through t...
A maioria das propostas de planejamento de rotas para robôs móveis não leva em conta a existência de...
Formal methods based on the Markov decision process formalism, such as probabilistic computation tre...
Applying deep reinforcement learning to physical systems, as opposed to learning in simulation, pres...
In the real world, robots operate with imperfect sensors providing uncertain and incomplete informat...
Task learning in robotics requires repeatedly executing the same actions in different states to lear...
In my presentation I will present my research study which investigates artificial intelligence techn...
Abstract — We present a learning system which is able to quickly and reliably acquire a robust feedb...
In order for human-assisting robots to be deployed in the real world such as household environments,...
PhD thesisIn this thesis, we argue that autonomous robots operating in hostile and uncertain environ...
Keeping risk under control is a primary objective in many critical real-world domains, including fin...
Abstract — Task learning in robotics is a time-consuming process, and model-based reinforcement lear...
A central goal of the robotics community is to develop general optimization algorithms for producing...
Model-free reinforcement learning has recently been shown to be effective at learning navigation pol...