While deep reinforcement learning (RL) algorithms have been successfully...
Reinforcement Learning (RL) environments can produce training data with
...
We consider the problem of off-policy evaluation (OPE) in reinforcement
...
In various control task domains, existing controllers provide a baseline...
Machine learning is rapidly being used in database research to improve t...
This paper studies the problem of data collection for policy evaluation ...
This paper considers how to complement offline reinforcement learning (R...
Recognising the goals or intentions of observed vehicles is a key step
t...
Robot control policies learned in simulation do not often transfer well ...
Robots can learn to do complex tasks in simulation, but often, learned
b...
Current methods for authentication based on public-key cryptography are
...
Imitation learning has long been an approach to alleviate the tractabili...
We consider the task of evaluating a policy for a Markov decision proces...
For an autonomous agent, executing a poor policy may be costly or even
d...