In recent years, deep artificial neural networks (including recurrent ones) have won
numerous contests in pattern recognition and machine learning. This historical survey …

Function approximation is essential to reinforcement learning, but the standard approach of
approximating a value function and deter (cid: 173) mining a policy from it has so far proven …

We consider the fully decentralized multi-agent reinforcement learning (MARL) problem,
where the agents are connected via a time-varying and possibly sparse communication …

Reinforcement learning is an appealing approach for allowing robots to learn new tasks.
Relevant literature reveals a plethora of methods, but at the same time makes clear the lack …

While policy-based reinforcement learning (RL) achieves tremendous successes in practice,
it is significantly less understood in theory, especially compared with value-based RL. In …

We provide a natural gradient method that represents the steepest descent direction based
on the underlying structure of the param (cid: 173) eter space. Although gradient methods …

Abstract A Markov Decision Process (MDP) is a natural framework for formulating sequential
decision-making problems under uncertainty. In recent years, researchers have greatly …

Policy gradient methods with actor-critic schemes demonstrate tremendous empirical
successes, especially when the actors and critics are parameterized by neural networks …

Training directed neural networks typically requires forward-propagating data through a
computation graph, followed by backpropagating error signal, to produce weight updates. All …

The acquisition and improvement of motor skills and control policies for robotics from trial
and error is of essential importance if robots should ever leave precisely pre-structured …