Add to ORKGOne of the main challenges in AI is performing dynamic tasks by using approaches that efficiently predict the environment’s future outcomes. State-of-the-art planners can reason effectively with symbolic representations of the environment. However, when the environment is continuous and unstructured, manually extracting an ad-hoc symbolic model to perform planning may be infeasible. Deep Reinforcement Learning is known to automatically learn compact representations of the state space through interaction with the environment. However, it is not suitable for planning, giving up the efficiency we would gain by predicting the consequences of actions. This work focuses on continuous state-space MDPs and proposes an approach that naturally combin...
Autonomous agents embedded in a physical environment need the ability to recognize objects and their...
Deep reinforcement learning (DRL) has gained great success by learning directly from high-dimensiona...
This thesis demonstrates how the power of symbolic processing can be exploited in the learning of lo...
One of the main challenges in AI is performing dynamic tasks by using approaches that efficiently pr...
Long-living autonomous agents must be able to learn to perform competently in novel environments. On...
We consider the problem of constructing a symbolic description of a continuous, low-level environmen...
We consider the problem of how to plan efficiently in low-level, continuous state spaces with tempor...
Symbolic representations have been used successfully in off-line planning algorithms for Markov deci...
Symbolic representations have been used successfully in off-line planning algorithms for Markov deci...
In this article, we work towards the goal of developing agents that can learn to act in complex worl...
Despite of achieving great success in real life, Deep Reinforcement Learning (DRL) is still sufferin...
Deep reinforcement learning (DRL) has gained great success by learning directly from high-dimensiona...
Current domain-independent, classical planners require symbolic models of the problem domain and ins...
Abstract—This work aims for bottom-up and autonomous development of symbolic planning operators from...
An autonomous agent should make good decisions quickly. These two considerations --- effectiveness a...
Autonomous agents embedded in a physical environment need the ability to recognize objects and their...
Deep reinforcement learning (DRL) has gained great success by learning directly from high-dimensiona...
This thesis demonstrates how the power of symbolic processing can be exploited in the learning of lo...
One of the main challenges in AI is performing dynamic tasks by using approaches that efficiently pr...
Long-living autonomous agents must be able to learn to perform competently in novel environments. On...
We consider the problem of constructing a symbolic description of a continuous, low-level environmen...
We consider the problem of how to plan efficiently in low-level, continuous state spaces with tempor...
Symbolic representations have been used successfully in off-line planning algorithms for Markov deci...
Symbolic representations have been used successfully in off-line planning algorithms for Markov deci...
In this article, we work towards the goal of developing agents that can learn to act in complex worl...
Despite of achieving great success in real life, Deep Reinforcement Learning (DRL) is still sufferin...
Deep reinforcement learning (DRL) has gained great success by learning directly from high-dimensiona...
Current domain-independent, classical planners require symbolic models of the problem domain and ins...
Abstract—This work aims for bottom-up and autonomous development of symbolic planning operators from...
An autonomous agent should make good decisions quickly. These two considerations --- effectiveness a...
Autonomous agents embedded in a physical environment need the ability to recognize objects and their...
Deep reinforcement learning (DRL) has gained great success by learning directly from high-dimensiona...
This thesis demonstrates how the power of symbolic processing can be exploited in the learning of lo...