arXiv subjects

Catholijn M. Jonker

Publications and source records attributed to Catholijn M. Jonker.

46 records · Page 3Linked to original sources

arXiv2018

Modelling Agents Endowed with Social Practices: Static Aspects

To understand societal phenomena through simulation, we need computational variants of socio-cognitive theories. Social Practice Theory has provided a unique understanding of social phenomena regarding the routinized, social and interconnected aspects of behaviour. This paper provides the Social Practice Agent (SoPrA) model that enables the use of Social Practice Theory (SPT) for agent-based simulations. We extract requirements from SPT, construct a computational model in the Unified Modelling Language, verify its implementation in Netlogo and Protégé and show how SoPrA maps on a use case of commuting. The next step is to model the dynamic aspect of SPT and validate SoPrA's ability to provide understanding in different scenario's. This paper provides the groundwork with a computational model that is a correct depiction of SPT, computational feasible and can be directly mapped to the habitual, social and interconnected aspects of a target scenario.

cs.MA↗

arXiv2018

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. We study network losses and propagation mechanisms for Gaussian, Categorical and Gaussian mixture distributions. Combined with exploration policies that leverage this return distribution, we solve, for example, a randomized Chain task of length 100, which has not been reported before when learning with neural networks.

cs.LG↗

arXiv2018

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. These games have a discrete action space. However, many real-world reinforcement learning domains have continuous action spaces, for example in robotic control, navigation and self-driving cars. This paper presents the necessary theoretical extensions of Alpha Zero to deal with continuous action space. We also provide some preliminary experiments on the Pendulum swing-up task, empirically showing the feasibility of our approach. Thereby, this work provides a first step towards the application of iterated search and learning in domains with a continuous action space.

stat.ML↗

arXiv2018

Volunteers in the Smart City: Comparison of Contribution Strategies on Human-Centered Measures

Several smart city services rely on users contribution, e.g., data, which can be costly for the users in terms of privacy. High costs lead to reduced user participation, which undermine the success of smart city technologies. This work develops a scenario-independent design principle, based on public good theory, for resource management in smart city applications, where provision of a service depends on contributors and free-riders, which benefit from the service without contributing own resources. Following this design principle, different classes of algorithms for resource management are evaluated with respect to human-centered measures, i.e., privacy, fairness and social welfare. Trade-offs that characterize algorithms are discussed across two smart city application scenarios. These results might help Smart City application designers to choose a suitable algorithm given a scenario-specific set of requirements, and users to choose a service based on an algorithm that matches their preferences.

cs.MA↗

arXiv2018

Monte Carlo Tree Search for Asymmetric Trees

We present an extension of Monte Carlo Tree Search (MCTS) that strongly increases its efficiency for trees with asymmetry and/or loops. Asymmetric termination of search trees introduces a type of uncertainty for which the standard upper confidence bound (UCB) formula does not account. Our first algorithm (MCTS-T), which assumes a non-stochastic environment, backs-up tree structure uncertainty and leverages it for exploration in a modified UCB formula. Results show vastly improved efficiency in a well-known asymmetric domain in which MCTS performs arbitrarily bad. Next, we connect the ideas about asymmetric termination to the presence of loops in the tree, where the same state appears multiple times in a single trace. An extension to our algorithm (MCTS-T+), which in addition to non-stochasticity assumes full state observability, further increases search efficiency for domains with loops as well. Benchmark testing on a set of OpenAI Gym and Atari 2600 games indicates that our algorithms always perform better than or at least equivalent to standard MCTS, and could be first-choice tree search algorithms for non-stochastic, fully-observable environments.

stat.ML↗

arXiv2017

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. We identify two sources of uncertainty that are relevant for exploration. The first originates from limited data (parametric uncertainty), while the second originates from the distribution of the returns (return uncertainty). We identify methods to learn these distributions with deep neural networks, where we estimate parametric uncertainty with Bayesian drop-out, while return uncertainty is propagated through the Bellman equation as a Gaussian distribution. Then, we identify that both can be jointly estimated in one network, which we call the Double Uncertain Value Network. The policy is directly derived from the learned distributions based on Thompson sampling. Experimental results show that both types of uncertainty may vastly improve learning in domains with a strong exploration challenge.

cs.LG↗

arXiv2017

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. We focus on evaluating transition function estimation, while we defer planning over this model to future work. Stochasticity is a fundamental property of many task environments. However, discriminative function approximators have difficulty estimating multimodal stochasticity. In contrast, deep generative models do capture complex high-dimensional outcome distributions. First we discuss why, amongst such models, conditional variational inference (VI) is theoretically most appealing for model-based RL. Subsequently, we compare different VI models on their ability to learn complex stochasticity on simulated functions, as well as on a typical RL gridworld with multimodal dynamics. Results show VI successfully predicts multimodal outcomes, but also robustly ignores these for deterministic parts of the transition dynamics. In summary, we show a robust method to learn multimodal transitions using function approximation, which is a key preliminary for model-based RL in stochastic domains.

stat.ML↗

arXiv2017

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. The survey focuses on agent/robot emotions, and mostly ignores human user emotions. Emotions are recognized as functional in decision-making by influencing motivation and action selection. Therefore, computational emotion models are usually grounded in the agent's decision making architecture, of which RL is an important subclass. Studying emotions in RL-based agents is useful for three research fields. For machine learning (ML) researchers, emotion models may improve learning efficiency. For the interactive ML and human-robot interaction (HRI) community, emotions can communicate state and enhance user investment. Lastly, it allows affective modelling (AM) researchers to investigate their emotion theories in a successful AI agent class. This survey provides background on emotion theory and RL. It systematically addresses 1) from what underlying dimensions (e.g., homeostasis, appraisal) emotions can be derived and how these can be modelled in RL-agents, 2) what types of emotions have been derived from these dimensions, and 3) how these emotions may either influence the learning efficiency of the agent or be useful as social signals. We also systematically compare evaluation criteria, and draw connections to important RL sub-domains like (intrinsic) motivation and model-based RL. In short, this survey provides both a practical overview for engineers wanting to implement emotions in their RL agents, and identifies challenges and directions for future emotion-RL research.

cs.LG↗

arXiv2017

PriMaL: A Privacy-Preserving Machine Learning Method for Event Detection in Distributed Sensor Networks

This paper introduces PriMaL, a general PRIvacy-preserving MAchine-Learning method for reducing the privacy cost of information transmitted through a network. Distributed sensor networks are often used for automated classification and detection of abnormal events in high-stakes situations, e.g. fire in buildings, earthquakes, or crowd disasters. Such networks might transmit privacy-sensitive information, e.g. GPS location of smartphones, which might be disclosed if the network is compromised. Privacy concerns might slow down the adoption of the technology, in particular in the scenario of social sensing where participation is voluntary, thus solutions are needed which improve privacy without compromising on the event detection accuracy. PriMaL is implemented as a machine-learning layer that works on top of an existing event detection algorithm. Experiments are run in a general simulation framework, for several network topologies and parameter values. The privacy footprint of state-of-the-art event detection algorithms is compared within the proposed framework. Results show that PriMaL is able to reduce the privacy cost of a distributed event detection algorithm below that of the corresponding centralized algorithm, within the bounds of some assumptions about the protocol. Moreover the performance of the distributed algorithm is not statistically worse than that of the centralized algorithm.

cs.DC↗

arXiv2016

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. Sometimes, this may prove to be a difficult task (e.g., conflict, mistrust, no information sharing, etc.). In this paper, we explore the possibility of achieving Pareto Optimal outcomes in a group by using a bottom-up approach: discovering Pareto optimal outcomes by interacting in subgroups. We analytically show that Pareto optimal outcomes in a subgroup are also Pareto optimal in a supergroup of those agents in the case of strict, transitive, and complete preferences. Then, we empirically analyze the prospective usability and practicality of bottom-up approaches in a variety of decision making domains.

cs.MA↗