Zobrazeno 1 - 10
of 64
pro vyhledávání: '"Richard Dazeley"'
Publikováno v:
Journal of Open Research Software, Vol 11, Iss 1, Pp 8-8 (2023)
This paper describes a language wrapper for the NetHack Learning Environment (NLE) [1]. The wrapper replaces the non-language observations and actions with comparable language versions. The NLE offers a grand challenge for AI research while MiniHack
Externí odkaz:
https://doaj.org/article/16bcc563ecfa4def93f99613e489f229
Publikováno v:
Sensors, Vol 23, Iss 5, p 2681 (2023)
Deep Reinforcement Learning (DeepRL) methods have been widely used in robotics to learn about the environment and acquire behaviours autonomously. Deep Interactive Reinforcement 2 Learning (DeepIRL) includes interactive feedback from an external trai
Externí odkaz:
https://doaj.org/article/f66e768d39ca489d9fe912c6b3915f82
Autor:
Cristian C. Millan-Arias, Bruno J. T. Fernandes, Francisco Cruz, Richard Dazeley, Sergio Fernandes
Publikováno v:
IEEE Access, Vol 9, Pp 104242-104260 (2021)
Reinforcement learning refers to a machine learning paradigm in which an agent interacts with the environment to learn how to perform a task. The characteristics of the environment may change over time or be affected by disturbances not controlled, a
Externí odkaz:
https://doaj.org/article/5d8c9207e5434d8f855f4be7660ddbe6
Publikováno v:
Biomimetics, Vol 6, Iss 1, p 13 (2021)
Interactive reinforcement learning methods utilise an external information source to evaluate decisions and accelerate learning. Previous work has shown that human advice could significantly improve learning agents’ performance. When evaluating rei
Externí odkaz:
https://doaj.org/article/17ff960e64d642e9a486d03b78b5358b
Publikováno v:
Applied Sciences, Vol 10, Iss 16, p 5574 (2020)
Robots are extending their presence in domestic environments every day, it being more common to see them carrying out tasks in home scenarios. In the future, robots are expected to increasingly perform more complex tasks and, therefore, be able to ac
Externí odkaz:
https://doaj.org/article/6ff99798122f4c6281537d9ce553f4a1
Publikováno v:
Neural Computing and Applications.
For an Artificially Intelligent (AI) system to maintain alignment between human desires and its behaviour, it is important that the AI account for human preferences. This paper proposes and empirically evaluates the first approach to aligning agent b
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d65b08db34a3bc9551737f2eb88145c3
https://doi.org/10.1007/s00521-023-08586-x
https://doi.org/10.1007/s00521-023-08586-x
Publikováno v:
Neural Computing and Applications.
Broad Explainable Artificial Intelligence moves away from interpreting individual decisions based on a single datum and aims to provide integrated explanations from multiple machine learning algorithms into a coherent explanation of an agent's behavi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5bbaa8d8d47d65f728a739e6a657277b
https://doi.org/10.1007/s00521-023-08423-1
https://doi.org/10.1007/s00521-023-08423-1
Publikováno v:
Neural Computing and Applications. 34:1713-1733
Neural networks are effective function approximators, but hard to train in the reinforcement learning (RL) context mainly because samples are correlated. In complex problems, a neural RL approach is often able to learn a better solution than tabular
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d40302fa0487118da231bfcd77c8d8ce
https://doi.org/10.1007/s00521-021-06270-6
https://doi.org/10.1007/s00521-021-06270-6
Autor:
Richard Dazeley, Francisco Cruz, Peter Vamplew, Matthew D. Taylor, Tim Brys, Cameron Foale, Adam Bignold
Publikováno v:
Journal of Ambient Intelligence and Humanized Computing. 14:3621-3644
A long-term goal of reinforcement learning agents is to be able to perform tasks in complex real-world scenarios. The use of external information is one way of scaling agents to more complex problems. However, there is a general lack of collaboration
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f4dd6ca8ecd57822569b02e88ad42fa0
https://doi.org/10.1007/s12652-021-03489-y
https://doi.org/10.1007/s12652-021-03489-y
In this study, we used grammatical evolution to develop a customised particle swarm optimiser by incorporating adaptive building blocks. This makes the algorithm self-adaptable to the problem instance. Our objective is to provide the means to automat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bfa8137fe7c2a74be88827f10cc1e9ff
https://doi.org/10.21203/rs.3.rs-1215035/v1
https://doi.org/10.21203/rs.3.rs-1215035/v1
