Skill-based reinforcement learning (RL) has emerged as a promising strategy to leverage prior knowledge for accelerated robot learning. Skills are typically extracted from expert demonstrations and are embedded into a latent space from which they can be sampled as actions by a high-level RL agent. However, this skill space is expansive, and not all skills are relevant for a given robot state, making exploration difficult. Furthermore, the downstream RL agent is limited to learning structurally similar tasks to those used to construct the skill space. We firstly propose accelerating exploration in the skill space using state-conditioned generative models to directly bias the high-level agent towards only sampling skills relevant to a given s...
Modern robotic applications create high demands on adaptation of actions with respect to variance in...
Practising and honing skills forms a fundamental component of how humans learn, yet artificial agent...
We present a data-efficient framework for solving sequential decision-making problems which exploits...
Skill-based reinforcement learning (RL) has emerged as a promising strategy to leverage prior knowle...
Skill-based reinforcement learning (RL) has emerged as a promising strategy to leverage prior knowle...
Advancements in robotics and artificial intelligence have paved the way for autonomous agents to per...
Among the most impressive of aspects of human intelligence is skill acquisition—the ability to ident...
For robots to perform tasks in the unstructured environments of the real world, they must be able to...
In the past few years, deep reinforcement learning (RL) has shown great potential in learning action...
Typical reinforcement learning (RL) agents learn to complete tasks specified by reward functions tai...
Robot acquiring skill is a process similar to human skill learning. Reinforcement learning (RL) is a...
Current reinforcement learning (RL) in robotics often experiences difficulty in generalizing to new ...
Mobile robots are increasingly being employed for performing complex tasks in dynamic environments. ...
Robust and generalizable robots that can autonomously manipulate objects in semi-structured environm...
Autonomous robots that can assist humans in situations of daily life have been a long standing visio...
Modern robotic applications create high demands on adaptation of actions with respect to variance in...
Practising and honing skills forms a fundamental component of how humans learn, yet artificial agent...
We present a data-efficient framework for solving sequential decision-making problems which exploits...
Skill-based reinforcement learning (RL) has emerged as a promising strategy to leverage prior knowle...
Skill-based reinforcement learning (RL) has emerged as a promising strategy to leverage prior knowle...
Advancements in robotics and artificial intelligence have paved the way for autonomous agents to per...
Among the most impressive of aspects of human intelligence is skill acquisition—the ability to ident...
For robots to perform tasks in the unstructured environments of the real world, they must be able to...
In the past few years, deep reinforcement learning (RL) has shown great potential in learning action...
Typical reinforcement learning (RL) agents learn to complete tasks specified by reward functions tai...
Robot acquiring skill is a process similar to human skill learning. Reinforcement learning (RL) is a...
Current reinforcement learning (RL) in robotics often experiences difficulty in generalizing to new ...
Mobile robots are increasingly being employed for performing complex tasks in dynamic environments. ...
Robust and generalizable robots that can autonomously manipulate objects in semi-structured environm...
Autonomous robots that can assist humans in situations of daily life have been a long standing visio...
Modern robotic applications create high demands on adaptation of actions with respect to variance in...
Practising and honing skills forms a fundamental component of how humans learn, yet artificial agent...
We present a data-efficient framework for solving sequential decision-making problems which exploits...