Search Results for author:
Found 33 papers, 10 papers with code
Towards General Negotiation Strategies with End-to-End Reinforcement Learning
We developed an end-to-end reinforcement learning method for diverse negotiation problems by representing observations and actions as a graph and applying graph neural networks in the policy.
A Hybrid Intelligence Method for Argument Mining
We find that, on the one hand, HyEnA achieves higher coverage and precision than a state-of-the-art automated method when compared to a common set of diverse opinions, justifying the need for human insight.
Value Preferences Estimation and Disambiguation in Hybrid Participatory Systems
We focus on situations where a conflict is detected between participants' choices and motivations, and propose methods for estimating value preferences while addressing detected inconsistencies by interacting with the participants.
An Empirical Analysis of Diversity in Argument Summarization
Presenting high-level arguments is a crucial task for fostering participation in online societal discussions.
A Systematic Review on Fostering Appropriate Trust in Human-AI Interaction
Appropriate Trust in Artificial Intelligence (AI) systems has rapidly become an important area of focus for both researchers and practitioners.
Do Differences in Values Influence Disagreements in Online Discussions?
We investigate a hypothesis that differences in personal values are indicative of disagreement in online discussions.
Reflective Hybrid Intelligence for Meaningful Human Control in Decision-Support Systems
With the growing capabilities and pervasiveness of AI systems, societies must collectively choose between reduced human autonomy, endangered democracies and limited human rights, and AI that is aligned to human and social values, nurturing collaboration, resilience, knowledge and ethical behaviour.
AI Alignment Dialogues: An Interactive Approach to AI Alignment in Support Agents
Most of the current approach to AI alignment is to learn what humans value from their behavioural data.
Exploring Effectiveness of Explanations for Appropriate Trust: Lessons from Cognitive Psychology
We identify four components to which explanation designers can pay special attention: perception, semantics, intent, and user & context.
MOPaC: The Multiple Offers Protocol for Multilateral Negotiations with Partial Consensus
Existing protocols for multilateral negotiation require a full consensus among the negotiating parties.
Towards a Real-time Measure of the Perception of Anthropomorphism in Human-robot Interaction
43 English-speaking participants took part in the study for whom we analysed the degree of acoustic-prosodic entrainment to the human or robot face, respectively.
Meaningful human control: actionable properties for AI system development
The concept of meaningful human control has been proposed to address responsibility gaps and mitigate them by establishing conditions that enable a proper attribution of responsibility for humans; however, clear requirements for researchers, designers, and engineers are yet inexistent, making the development of AI-based systems that remain under meaningful human control challenging.
Towards Social Situation Awareness in Support Agents
Since many daily activities are social in nature, support agents should understand a user's social situation to offer comprehensive support.
Using Psychological Characteristics of Situations for Social Situation Comprehension in Support Agents
First, from a technical perspective, we show that psychological characteristics of situations can be used as input to predict the priority of social situations, and that psychological characteristics of situations can be predicted from the features of a social situation.
From Organisational Structure to Organisational Behaviour Formalisation
It is shown how for different aggregation levels and other elements within an organisation structure, sets of dynamic properties can be specified.
Reason Against the Machine: Future Directions for Mass Online Deliberation
Designers of online deliberative platforms aim to counter the degrading quality of online debates.
A Data-Driven Method for Recognizing Automated Negotiation Strategies
Our approach includes a data generation method for an agent to generate domain-independent sequences by negotiating with a variety of opponents across domains, a feature engineering method for representing negotiation data as time series with time-step features and overall features, and a hybrid (recurrent neural network-based) deep learning method for recognizing an opponent's strategy from the time series of bids.
Synthesising Reinforcement Learning Policies through Set-Valued Inductive Rule Learning
Then, to ensure that the rules explain a valid, non-degenerate policy, we introduce a refinement algorithm that fine-tunes the rules to obtain good performance when executed in the environment.
More Similar Values, More Trust? -- the Effect of Value Similarity on Trust in Human-Agent Interaction
To achieve this, it is first important to understand which factors influence trust in AI.
Modelling Human Routines: Conceptualising Social Practice Theory for Agent-Based Simulation
This paper provides the domain-independent Social Practice Agent (SoPrA) framework that satisfies requirements from the literature to simulate our routines.
Model-based Reinforcement Learning: A Survey
Two key approaches to this problem are reinforcement learning (RL) and planning.
A Unifying Framework for Reinforcement Learning and Planning
Therefore, this paper presents a unifying algorithmic framework for reinforcement learning and planning (FRAP), which identifies underlying dimensions on which MDP planning and learning algorithms have to decide.
The Second Type of Uncertainty in Monte Carlo Tree Search
Monte Carlo Tree Search (MCTS) efficiently balances exploration and exploitation in tree search based on count-derived uncertainty.
Think Too Fast Nor Too Slow: The Computational Trade-off Between Planning And Reinforcement Learning
Planning and reinforcement learning are two key approaches to sequential decision making.
Automated Configuration of Negotiation Strategies
By empowering automated negotiating agents using automated algorithm configuration, we obtain a flexible negotiation agent that can be configured automatically for a rich space of opponents and negotiation scenarios.
The Potential of the Return Distribution for Exploration in RL
This paper studies the potential of the return distribution for exploration in deterministic reinforcement learning (RL) environments.
A0C: Alpha Zero in Continuous Action Space
A core novelty of Alpha Zero is the interleaving of tree search and deep learning, which has proven very successful in board games like Chess, Shogi and Go.
Monte Carlo Tree Search for Asymmetric Trees
Asymmetric termination of search trees introduces a type of uncertainty for which the standard upper confidence bound (UCB) formula does not account.
Ordered Preference Elicitation Strategies for Supporting Multi-Objective Decision Making
We build on previous work on Gaussian processes and pairwise comparisons for preference modelling, extend it to the multi-objective decision support scenario, and propose new ordered preference elicitation strategies based on ranking and clustering.
Efficient exploration with Double Uncertain Value Networks
This paper studies directed exploration for reinforcement learning agents by tracking uncertainty about the value of each available action.
Emotion in Reinforcement Learning Agents and Robots: A Survey
This article provides the first survey of computational models of emotion in reinforcement learning (RL) agents.
Learning Multimodal Transition Dynamics for Model-Based Reinforcement Learning
In this paper we study how to learn stochastic, multimodal transition dynamics in reinforcement learning (RL) tasks.
Model-based Reinforcement Learning
reinforcement-learning
+2
Can we reach Pareto optimal outcomes using bottom-up approaches?
Traditionally, researchers in decision making have focused on attempting to reach Pareto Optimality using horizontal approaches, where optimality is calculated taking into account every participant at the same time.
