In this paper, we suggest a novel reinforcement learning architecture, the Natural Actor-
Critic. The actor updates are achieved using stochastic policy gradients employing Amari's …

This paper investigates a novel model-free reinforcement learning architecture, the Natural
Actor-Critic. The actor updates are based on stochastic policy gradients employing Amari's …

For many tasks, tactile or visual feedback is helpful or even crucial. However, designing
controllers that take such high-dimensional feedback into account is non-trivial. Therefore …

In this paper, we propose a novel policy iteration method, called dynamic policy
programming (DPP), to estimate the optimal policy in the infinite-horizon Markov decision …

Collective behaviours such as swarm formation of autonomous agents offer the advantages
of efficient movement, redundancy, and potential for human guidance of a single swarm …

Autonomous robots that can assist humans in situations of daily life have been a long
standing vision of robotics, artificial intelligence, and cognitive sciences. In this thesis, we …

In this paper, we consider the problem of planning in the infinite-horizon discounted-reward
Markov decision problems. We propose a novel iterative method, called dynamic policy …

Learning complex control policies from non-linear and redundant sensory input is an
important challenge for reinforcement learning algorithms. Non-parametric methods that …

摘要自动驾驶车辆的本质是轮式移动机器人, 是一个集模式识别, 环境感知,
规划决策和智能控制等功能于一体的综合系统. 人工智能和机器学习领域的进步极大推动了自动 …

We present a new class of structured reinforcement learning policy-architectures, Implicit
Two-Tower (ITT) policies, where the actions are chosen based on the attention scores of …