Deep reinforcement learning algorithms typically require large amounts of data to solve a specific problem, and do not generalize well to other tasks. Recent methods in unsupervised reinforcement learning can learn a range of different behaviors within an environment without the use of task-specific data. This could be helpful in situations where designing many different task objectives and experiments, or acquiring labeled data is costly. In this work we study unsupervised reinforcement learning in a simulated robotics environment, where the agent takes continuous valued actions. We propose an adaptation of a recent method in unsupervised reinforcement learning to continuous action environments. The goal is to learn a set of skills which c...
Robots are expected to become an increasingly common part of most humans everyday lives. As the numb...
Robots are expected to become an increasingly common part of most humans everyday lives. As the numb...
Robots are expected to become an increasingly common part of most humans everyday lives. As the numb...
Deep reinforcement learning algorithms typically require large amounts of data to solve a specific p...
Deep reinforcement learning has been shown to be a potential alternative to a traditional controller...
Deep reinforcement learning has been shown to be a potential alternative to a traditional controller...
Det å forbedre roboters autonomi har lenge vært et mål for forskere. Ulike verktøy har blitt brukt f...
In this thesis, we used deep reinforcement learning to train autonomous agents and evaluated the imp...
In this thesis, we used deep reinforcement learning to train autonomous agents and evaluated the imp...
Robots are becoming more ubiquitous in our society and taking over many tasks that were previously c...
Robots are becoming more ubiquitous in our society and taking over many tasks that were previously c...
Robots are becoming more ubiquitous in our society and taking over many tasks that were previously c...
In this thesis, we used deep reinforcement learning to train autonomous agents and evaluated the imp...
Reinforcement learning (RL) is one of the three main areas in machine learning (ML) with a solid the...
Reinforcement learning (RL) is one of the three main areas in machine learning (ML) with a solid the...
Robots are expected to become an increasingly common part of most humans everyday lives. As the numb...
Robots are expected to become an increasingly common part of most humans everyday lives. As the numb...
Robots are expected to become an increasingly common part of most humans everyday lives. As the numb...
Deep reinforcement learning algorithms typically require large amounts of data to solve a specific p...
Deep reinforcement learning has been shown to be a potential alternative to a traditional controller...
Deep reinforcement learning has been shown to be a potential alternative to a traditional controller...
Det å forbedre roboters autonomi har lenge vært et mål for forskere. Ulike verktøy har blitt brukt f...
In this thesis, we used deep reinforcement learning to train autonomous agents and evaluated the imp...
In this thesis, we used deep reinforcement learning to train autonomous agents and evaluated the imp...
Robots are becoming more ubiquitous in our society and taking over many tasks that were previously c...
Robots are becoming more ubiquitous in our society and taking over many tasks that were previously c...
Robots are becoming more ubiquitous in our society and taking over many tasks that were previously c...
In this thesis, we used deep reinforcement learning to train autonomous agents and evaluated the imp...
Reinforcement learning (RL) is one of the three main areas in machine learning (ML) with a solid the...
Reinforcement learning (RL) is one of the three main areas in machine learning (ML) with a solid the...
Robots are expected to become an increasingly common part of most humans everyday lives. As the numb...
Robots are expected to become an increasingly common part of most humans everyday lives. As the numb...
Robots are expected to become an increasingly common part of most humans everyday lives. As the numb...