Cooperative multi-agent reinforcement learning often requires decentralised policies, which
severely limit the agents' ability to coordinate their behaviour. In this paper, we show that …

… for multiagent reinforcement learning. A common feature of these algorithms is a parameterized,
structured representation of a policy or value function. This structure is leveraged in an …

… In order to learn a representation for actions that captures this structure, we consider a …
A common method for learning a policy parameterized with weights θ is to optimize the …

… We then formulate structure as a particular kind of side … of incorporating structure into the RL
learning process and … research while providing a common reference point for understanding …

Deep reinforcement learning (RL) methods have driven impressive advances in artificial
intelligence in recent years, exceeding human performance in domains ranging from Atari to Go …

… We reveal common system structures and create a meta-model for capacity … structures)
from common system structures or learn them from related domains or problems, future learning …

Cooperative multi-agent reinforcement learning often requires decentralised policies, which
severely limit the agents' ability to coordinate their behaviour. In this paper, we show that …

… they take advantage of the special structure of reinforcement-learning problems that is not
… A very common formulation of cost functions in adaptive control are quadratic penalties on …

… -critic structure, which leads to a large number of advanced deep reinforcement learning
algorithms. … of terminology for common contents in reinforcement learning is provided as follows: …

… learning that gains efficiency by capitalizing on task structure. … experiment we report) employ
a common set of methods, with … Our approach aims to learn a structure-dependent bandit …