Add to ORKGLearning near-optimal behaviour from an expert's demonstrations typically relies on the assumption that the learner knows the features that the true reward function depends on. In this paper, we study the problem of learning from demonstrations in the setting where this is not the case, i.e., where there is a mismatch between the worldviews of the learner and the expert. We introduce a natural quantity, the teaching risk, which measures the potential suboptimality of policies that look optimal to the learner in this setting. We show that bounds on the teaching risk guarantee that the learner is able to find a near-optimal policy using standard algorithms based on inverse reinforcement learning. Based on these findings, we suggest a teaching...
Inverse reinforcement learning (IRL) infers a reward function from demonstrations, allowing for poli...
We consider learning in a Markov decision process where we are not explicitly given a reward functio...
International audienceThis paper adresses the inverse reinforcement learning (IRL) problem, that is ...
As robots and other autonomous agents enter our homes, hospitals, schools, and workplaces, it is imp...
In the field of reinforcement learning there has been recent progress towards safety and high-confid...
We propose a novel formulation for the Inverse Reinforcement Learning (IRL) problem, which jointly a...
The task of learning a reward function from expert demonstrations suffers from high sample complexit...
We study the problem of learning a policy in a Markov decision process (MDP) based on observations o...
Reinforcement Learning (RL) methods provide a solution for decision-making problems under uncertaint...
The field of Reinforcement Learning is concerned with teaching agents to take optimal decisions t...
One of the fundamental problems of artificial intelligence is learning how to behave optimally. With...
We consider the problem of apprenticeship learning where the examples, demonstrated by an expert, co...
We consider the problem of apprenticeship learning where the examples, demonstrated by an expert, co...
We study the problem of inverse reinforcement learning (IRL) with the added twist that the learner i...
Learning desirable behavior from a limited number of demonstrations, also known as inverse reinforce...
Inverse reinforcement learning (IRL) infers a reward function from demonstrations, allowing for poli...
We consider learning in a Markov decision process where we are not explicitly given a reward functio...
International audienceThis paper adresses the inverse reinforcement learning (IRL) problem, that is ...
As robots and other autonomous agents enter our homes, hospitals, schools, and workplaces, it is imp...
In the field of reinforcement learning there has been recent progress towards safety and high-confid...
We propose a novel formulation for the Inverse Reinforcement Learning (IRL) problem, which jointly a...
The task of learning a reward function from expert demonstrations suffers from high sample complexit...
We study the problem of learning a policy in a Markov decision process (MDP) based on observations o...
Reinforcement Learning (RL) methods provide a solution for decision-making problems under uncertaint...
The field of Reinforcement Learning is concerned with teaching agents to take optimal decisions t...
One of the fundamental problems of artificial intelligence is learning how to behave optimally. With...
We consider the problem of apprenticeship learning where the examples, demonstrated by an expert, co...
We consider the problem of apprenticeship learning where the examples, demonstrated by an expert, co...
We study the problem of inverse reinforcement learning (IRL) with the added twist that the learner i...
Learning desirable behavior from a limited number of demonstrations, also known as inverse reinforce...
Inverse reinforcement learning (IRL) infers a reward function from demonstrations, allowing for poli...
We consider learning in a Markov decision process where we are not explicitly given a reward functio...
International audienceThis paper adresses the inverse reinforcement learning (IRL) problem, that is ...