Results 281 to 290 of about 198,528 (317)

Learning Pessimism for Reinforcement Learning

Proceedings of the AAAI Conference on Artificial Intelligence, 2023
Off-policy deep reinforcement learning algorithms commonly compensate for overestimation bias during temporal-difference learning by utilizing pessimistic estimates of the expected target returns. In this work, we propose Generalized Pessimism Learning (GPL), a strategy employing a novel learnable penalty to enact such pessimism.
Edoardo Cetin, Oya Çeliktutan
openaire   +1 more source

Reinforcement Learning in Swarms that Learn

IEEE/WIC/ACM International Conference on Intelligent Agent Technology, 2006
This paper introduces an approach to reinforcement learning by cooperating agents using a variation of the actor critic method. This is made possible by considering behavior patterns of swarms in the context of approximation spaces. Rough set theory introduced by Zdzislaw Pawlak in 1982 provides a ground for deriving pattern-based rewards within ...
James F. Peters, Christopher J. Henry, Sheela Ramanna   +2 more
openaire   +1 more source

Observational Learning by Reinforcement Learning

International Joint Conference on Autonomous Agents and Multiagent Systems, 2019
Observational learning is a type of learning that occurs as a function of observing, retaining and possibly imitating the behaviour of another agent. It is a core mechanism appearing in various instances of social learning and has been found to be employed in several intelligent species, including humans.
Diana Borsa, Nicolas Heess, Bilal Piot, Siqi Liu 0002, Leonard Hasenclever, Rémi Munos, Olivier Pietquin   +6 more
openaire   +2 more sources

Distributed Reinforcement Learning

Robotics and Autonomous Systems, 1995
In multi-agent systems two forms of learning can be distinguished: centralized learning, that is, learning done by a single agent independent of the other agents; and distributed learning, that is, learning that becomes possible only because several agents are present. Whereas centralized learning has been intensively studied in the field of artificial
openaire   +1 more source

Reinforcement Learning Agents

Artificial Intelligence Review, 2002
zbMATH Open Web Interface contents unavailable due to conflicting licenses.
openaire   +2 more sources

Reinforcement Learning and Deep Reinforcement Learning

2019
In order to better understand state-of-the-art reinforcement learning agent, deep Q-network, a brief review of reinforcement learning and Q-learning are first described. Then recent advances of deep Q-network are presented, and double deep Q-network and dueling deep Q-network that go beyond deep Q-network are also given.
F. Richard Yu, Ying He
openaire   +1 more source

Imitation and Reinforcement Learning

IEEE Robotics & Automation Magazine, 2010
In this article, we present both novel learning algorithms and experiments using the dynamical system MPs. As such, we describe this MP representation in a way that it is straightforward to reproduce. We review an appropriate imitation learning method, i.e., locally weighted regression, and show how this method can be used both for initializing RL ...
Jens Kober, Jan Peters 0001
openaire   +2 more sources

Learning Options in Reinforcement Learning

2002
Temporally extended actions (e.g., macro actions) have proven very useful for speeding up learning, ensuring robustness and building prior knowledge into AI systems. The options framework (Precup, 2000; Sutton, Precup & Singh, 1999) provides a natural way of incorporating such actions into reinforcement learning systems, but leaves open the issue of ...
Martin Stolle, Doina Precup
openaire   +1 more source

From Reinforcement Learning to Deep Reinforcement Learning: An Overview

2018
This article provides a brief overview of reinforcement learning, from its origins to current research trends, including deep reinforcement learning, with an emphasis on first principles.
Forest Agostinelli, Guillaume Hocquet, Sameer Singh 0001, Pierre Baldi   +3 more
openaire   +1 more source

Unsupervised Reinforcement Learning

International Joint Conference on Autonomous Agents and Multiagent Systems, 2020
Conventionally, reinforcement learning algorithms are goal-directed: they aim to acquire policies that most effectively maximize a given reward signal. However, if we consider agents that must master very large repertoires of behaviors -- such as general-purpose robots that must perform a diverse array of tasks in the real world -- then it makes sense ...
openaire   +2 more sources