It has long been established that predictive models can be transformed i...
Golden-section search and bisection search are the two main principled
a...
Levin Tree Search (LTS) is a search algorithm that makes use of a policy...
Memory-based meta-learning is a technique for approximating Bayes-optima...
We extend and combine several tools of the literature to design fast,
ad...
Traditional automated theorem provers for first-order logic depend on
sp...
The use of a policy and a heuristic function for guiding search can be q...
A major challenge in applying machine learning to automated theorem prov...
Designing reward functions is difficult: the designer has to specify wha...
The Lottery Ticket Hypothesis is a conjecture that every large neural ne...
A major challenge in applying machine learning to automated theorem prov...
In some agent designs like inverse reinforcement learning an agent needs...
We tackle two long-standing problems related to re-expansions in heurist...
We introduce and analyze two parameter-free linear-memory tree search
al...
The field of reinforcement learning (RL) is facing increasingly challeng...
We consider prediction with expert advice under the log-loss with the go...
We introduce two novel tree search algorithms that use a policy to guide...
How can we design reinforcement learning agents that avoid causing
unnec...
According to Dennett, the same system may be described using a `physical...
We present a suite of reinforcement learning environments illustrating
v...
No real-world reward function is perfect. Sensory errors and software bu...
We discuss a variant of Thompson sampling for nonparametric reinforcemen...