no code implementations • 9 Feb 2024 • Peter Vamplew, Cameron Foale, Richard Dazeley
Multi-objective reinforcement learning (MORL) algorithms extend conventional reinforcement learning (RL) to the more general case of problems with multiple, conflicting objectives, represented by vector-valued rewards.
no code implementations • 5 Feb 2024 • Peter Vamplew, Cameron Foale, Conor F. Hayes, Patrick Mannion, Enda Howley, Richard Dazeley, Scott Johnson, Johan Källström, Gabriel Ramos, Roxana Rădulescu, Willem Röpke, Diederik M. Roijers
Research in multi-objective reinforcement learning (MORL) has introduced the utility-based paradigm, which makes use of both environmental rewards and a function that defines the utility derived by the user from those rewards.
Multi-Objective Reinforcement Learning reinforcement-learning
no code implementations • 6 Jan 2024 • Kewen Ding, Peter Vamplew, Cameron Foale, Richard Dazeley
One common approach to solve multi-objective reinforcement learning (MORL) problems is to extend conventional Q-learning by using vector Q-values in combination with a utility function.
no code implementations • 30 May 2023 • Catalin Mitelut, Ben Smith, Peter Vamplew
The rapid advancement of artificial intelligence (AI) systems suggests that artificial general intelligence (AGI) systems may soon arrive.
no code implementations • 11 Oct 2022 • Francisco Cruz, Adam Bignold, Hung Son Nguyen, Richard Dazeley, Peter Vamplew
The use of interactive advice in reinforcement learning scenarios allows for speeding up the learning process for autonomous agents.
no code implementations • 7 Oct 2022 • Adrian Ly, Richard Dazeley, Peter Vamplew, Francisco Cruz, Sunil Aryal
However, divergent and unstable behaviour have been long standing issues in DQNs.
no code implementations • 7 Jul 2022 • Francisco Cruz, Charlotte Young, Richard Dazeley, Peter Vamplew
In this work, we make use of human-like explanations built from the probability of success to complete the goal that an autonomous robot shows after performing an action.
no code implementations • 20 Aug 2021 • Richard Dazeley, Peter Vamplew, Francisco Cruz
EXplainable RL (XRL) is relatively recent field of research that aims to develop techniques to extract concepts from the agent's: perception of the environment; intrinsic/extrinsic motivations/beliefs; Q-values, goals and objectives.
no code implementations • 7 Jul 2021 • Richard Dazeley, Peter Vamplew, Cameron Foale, Charlotte Young, Sunil Aryal, Francisco Cruz
Over the last few years there has been rapid research growth into eXplainable Artificial Intelligence (XAI) and the closely aligned Interpretable Machine Learning (IML).
1 code implementation • 17 Mar 2021 • Conor F. Hayes, Roxana Rădulescu, Eugenio Bargiacchi, Johan Källström, Matthew Macfarlane, Mathieu Reymond, Timothy Verstraeten, Luisa M. Zintgraf, Richard Dazeley, Fredrik Heintz, Enda Howley, Athirai A. Irissappane, Patrick Mannion, Ann Nowé, Gabriel Ramos, Marcello Restelli, Peter Vamplew, Diederik M. Roijers
Real-world decision-making tasks are generally complex, requiring trade-offs between multiple, often conflicting, objectives.
no code implementations • 4 Feb 2021 • Adam Bignold, Francisco Cruz, Richard Dazeley, Peter Vamplew, Cameron Foale
Interactive reinforcement learning has allowed speeding up the learning process in autonomous agents by including a human trainer providing extra information to the agent in real-time.
no code implementations • 21 Sep 2020 • Adam Bignold, Francisco Cruz, Richard Dazeley, Peter Vamplew, Cameron Foale
When interacting with a learner agent, humans may provide either evaluative or informative advice.
no code implementations • 3 Jul 2020 • Adam Bignold, Francisco Cruz, Matthew E. Taylor, Tim Brys, Richard Dazeley, Peter Vamplew, Cameron Foale
In this work, while reviewing externally-influenced methods, we propose a conceptual framework and taxonomy for assisted reinforcement learning, aimed at fostering collaboration by classifying and comparing various methods that use external information in the learning process.
no code implementations • 24 Jun 2020 • Francisco Cruz, Richard Dazeley, Peter Vamplew, Ithan Moreira
As a way to explain the goal-driven robot's actions, we use the probability of success computed by three different proposed approaches: memory-based, learning-based, and introspection-based.
1 code implementation • 5 May 2020 • Budi Kurniawan, Peter Vamplew, Michael Papasimeon, Richard Dazeley, Cameron Foale
It then selects from each discrete state an input value and the action with the highest numerical preference as an input/target pair.
no code implementations • 14 Apr 2020 • Peter Vamplew, Cameron Foale, Richard Dazeley
We report a previously unidentified issue with model-free, value-based approaches to multiobjective reinforcement learning in the context of environments with stochastic state transitions.
no code implementations • 8 Mar 2018 • Thanh Thi Nguyen, Ngoc Duy Nguyen, Peter Vamplew, Saeid Nahavandi, Richard Dazeley, Chee Peng Lim
This paper introduces a new scalable multi-objective deep reinforcement learning (MODRL) framework based on deep Q-networks.
Multi-Objective Reinforcement Learning reinforcement-learning
no code implementations • 4 Feb 2014 • Diederik Marijn Roijers, Peter Vamplew, Shimon Whiteson, Richard Dazeley
Using this taxonomy, we survey the literature on multi-objective methods for planning and learning.