Daniel Polani

Stas Tiomkin, Ilya Nemenman, Daniel Polani et al.

Biological systems often choose actions without an explicit reward signal, a phenomenon known as intrinsic motivation. The computational principles underlying this behavior remain poorly understood. In this study, we investigate an information-theoretic approach to intrinsic motivation, based on maximizing an agent's empowerment (the mutual information between its past actions and future states). We show that this approach generalizes previous attempts to formalize intrinsic motivation, and we provide a computationally efficient algorithm for computing the necessary quantities. We test our approach on several benchmark control problems, and we explain its success in guiding intrinsically motivated behaviors by relating our information-theoretic control function to fundamental properties of the dynamical system representing the combined agent-environment system. This opens the door for designing practical artificial, intrinsically motivated controllers and for linking animal behaviors to their dynamical properties.

Tristan Shah, Ilya Nemenman, Daniel Polani et al.

Intrinsic motivations are receiving increasing attention, i.e. behavioral incentives that are not engineered, but emerge from the interaction of an agent with its surroundings. In this work we study the emergence of behaviors driven by one such incentive, empowerment, specifically in the context of more than one agent. We formulate a principled extension of empowerment to the multi-agent setting, and demonstrate its efficient calculation. We observe that this intrinsic motivation gives rise to characteristic modes of group-organization in two qualitatively distinct environments: a pair of agents coupled by a tendon, and a controllable Vicsek flock. This demonstrates the potential of intrinsic motivations such as empowerment to not just drive behavior for only individual agents but also higher levels of behavioral organization at scale.

Phu Nguyen, Daniel Polani, Stas Tiomkin

The reward function is an essential component in robot learning. Reward directly affects the sample and computational complexity of learning, and the quality of a solution. The design of informative rewards requires domain knowledge, which is not always available. We use the properties of the dynamics to produce system-appropriate reward without adding external assumptions. Specifically, we explore an approach to utilize the Lyapunov exponents of the system dynamics to generate a system-immanent reward. We demonstrate that the `Sum of the Positive Lyapunov Exponents' (SuPLE) is a strong candidate for the design of such a reward. We develop a computational framework for the derivation of this reward, and demonstrate its effectiveness on classical benchmarks for sample-based stabilization of various dynamical systems. It eliminates the need to start the training trajectories at arbitrary states, also known as auxiliary exploration. While the latter is a common practice in simulated robot learning, it is unpractical to consider to use it in real robotic systems, since they typically start from natural rest states such as a pendulum at the bottom, a robot on the ground, etc. and can not be easily initialized at arbitrary states. Comparing the performance of SuPLE to commonly-used reward functions, we observe that the latter fail to find a solution without auxiliary exploration, even for the task of swinging up the double pendulum and keeping it stable at the upright position, a prototypical scenario for multi-linked robots. SuPLE-induced rewards for robot learning offer a novel route for effective robot learning in typical as opposed to highly specialized or fine-tuned scenarios. Our code is publicly available for reproducibility and further research.

Marcus M. Scheunemann, Sander G. van Dijk, Rebecca Miko et al.

We participated in the RoboCup 2018 competition in Montreal with our newly developed BoldBot based on the Darwin-OP and mostly self-printed custom parts. This paper is about the lessons learnt from that competition and further developments for the RoboCup 2019 competition. Firstly, we briefly introduce the team along with an overview of past achievements. We then present a simple, standalone 2D simulator we use for simplifying the entry for new members with making basic RoboCup concepts quickly accessible. We describe our approach for semantic-segmentation for our vision used in the 2018 competition, which replaced the lookup-table (LUT) implementation we had before. We also discuss the extra structural support we plan to add to the printed parts of the BoldBot and our transition to ROS 2 as our new middleware. Lastly, we will present a collection of open-source contributions of our team.

Philip Wilson, Axel Constant, Mahault Albarracin et al.

The proliferation of agentic artificial intelligence has outpaced the conceptual tools needed to characterize agency in computational systems. Prevailing definitions mainly rely on autonomy and goal-directedness. Here, we argue for a minimal notion open to principled inspection given three criteria: intentionality as action grounded in beliefs and desires, rationality as normatively coherent action entailed by a world model, and explainability as action causally traceable to internal states; we subsequently instantiate these as a partially observable Markov decision process under a variational framework wherein posterior beliefs, prior preferences, and the minimization of expected free energy jointly constitute an agentic action chain. Using a canonical T-maze paradigm, we evidence how empowerment, formulated as the channel capacity between actions and anticipated observations, serves as an operational metric that distinguishes zero-, intermediate-, and high-agency phenotypes through structural manipulations of the generative model. We conclude by arguing that as agents engage in epistemic foraging to resolve ambiguity, the governance controls that remain effective must shift systematically from external constraints to the internal modulation of prior preferences, offering a principled, variational bridge from computational phenotyping to AI governance strategy

Himaja Papala, Daniel Polani, Stas Tiomkin

Traffic congestion has long been an ubiquitous problem that is exacerbating with the rapid growth of megacities. In this proof-of-concept work we study intrinsic motivation, implemented via the empowerment principle, to control autonomous car behavior to improve traffic flow. In standard models of traffic dynamics, self-organized traffic jams emerge spontaneously from the individual behavior of cars, affecting traffic over long distances. Our novel car behavior strategy improves traffic flow while still being decentralized and using only locally available information without explicit coordination. Decentralization is essential for various reasons, not least to be able to absorb robustly substantial levels of uncertainty. Our scenario is based on the well-established traffic dynamics model, the Nagel-Schreckenberg cellular automaton. In a fraction of the cars in this model, we substitute the default behavior by empowerment, our intrinsic motivation-based method. This proposed model significantly improves overall traffic flow, mitigates congestion, and reduces the average traffic jam time.

Leonardo Christov-Moore, Arthur Juliani, Alex Kiefer et al.

Physical vulnerability and mortality are often seen as obstacles to be avoided in the development of artificial agents, which struggle to adapt to open-ended environments and provide aligned care. Meanwhile, biological organisms survive, thrive, and care for each other in an open-ended physical world with relative ease and efficiency. Understanding the role of the conditions of life in this disparity can aid in developing more robust, adaptive, and caring artificial agents. Here we define two minimal conditions for physical embodiment inspired by the existentialist phenomenology of Martin Heidegger: being-in-the-world (the agent is a part of the environment) and being-towards-death (unless counteracted, the agent drifts toward terminal states due to the second law of thermodynamics). We propose that from these conditions we can obtain both a homeostatic drive - aimed at maintaining integrity and avoiding death by expending energy to learn and act - and an intrinsic drive to continue to do so in as many ways as possible. Drawing inspiration from Friedrich Nietzsche's existentialist concept of will-to-power, we examine how intrinsic drives to maximize control over future states, e.g., empowerment, allow agents to increase the probability that they will be able to meet their future homeostatic needs, thereby enhancing their capacity to maintain physical integrity. We formalize these concepts within a reinforcement learning framework, which enables us to examine how intrinsically driven embodied agents learning in open-ended multi-agent environments may cultivate the capacities for open-endedness and care.

Karen Archer, Nicola Catenacci Volpi, Franziska Bröker et al.

Traditionally, Euclidean geometry is treated by scientists as a priori and objective. However, when we take the position of an agent, the problem of selecting a best route should also factor in the abilities of the agent, its embodiment and particularly its cognitive effort. In this paper we consider geometry in terms of travel between states within a world by incorporating information processing costs with the appropriate spatial distances. This induces a geometry that increasingly differs from the original geometry of the given world as information costs become increasingly important. We visualise this "cognitive geometry" by projecting it onto 2- and 3-dimensional spaces showing distinct distortions reflecting the emergence of epistemic and information-saving strategies as well as pivot states. The analogies between traditional cost-based geometries and those induced by additional informational costs invite a generalisation of the notion of geodesics as cheapest routes towards the notion of infodesics. In this perspective, the concept of infodesics is inspired by the property of geodesics that, travelling from a given start location to a given goal location along a geodesic, not only the goal, but all points along the way are visited at optimal cost from the start.

Fernando E. Rosas, Pedro A. M. Mediano, Martin Biehl et al.

We introduce a novel framework to identify perception-action loops (PALOs) directly from data based on the principles of computational mechanics. Our approach is based on the notion of causal blanket, which captures sensory and active variables as dynamical sufficient statistics -- i.e. as the "differences that make a difference." Moreover, our theory provides a broadly applicable procedure to construct PALOs that requires neither a steady-state nor Markovian dynamics. Using our theory, we show that every bipartite stochastic process has a causal blanket, but the extent to which this leads to an effective PALO formulation varies depending on the integrated information of the bipartition.

Yuqing Du, Stas Tiomkin, Emre Kiciman et al.

One difficulty in using artificial agents for human-assistive applications lies in the challenge of accurately assisting with a person's goal(s). Existing methods tend to rely on inferring the human's goal, which is challenging when there are many potential goals or when the set of candidate goals is difficult to identify. We propose a new paradigm for assistance by instead increasing the human's ability to control their environment, and formalize this approach by augmenting reinforcement learning with human empowerment. This task-agnostic objective preserves the person's autonomy and ability to achieve any eventual state. We test our approach against assistance based on goal inference, highlighting scenarios where our method overcomes failure modes stemming from goal ambiguity or misspecification. As existing methods for estimating empowerment in continuous domains are computationally hard, precluding its use in real time learned assistance, we also propose an efficient empowerment-inspired proxy metric. Using this, we are able to successfully demonstrate our method in a shared autonomy user study for a challenging simulated teleoperation task with human-in-the-loop training.

Marcus M. Scheunemann, Christoph Salge, Daniel Polani et al.

A challenge in using robots in human-inhabited environments is to design behavior that is engaging, yet robust to the perturbations induced by human interaction. Our idea is to imbue the robot with intrinsic motivation (IM) so that it can handle new situations and appears as a genuine social other to humans and thus be of more interest to a human interaction partner. Human-robot interaction (HRI) experiments mainly focus on scripted or teleoperated robots, that mimic characteristics such as IM to control isolated behavior factors. This article presents a "robotologist" study design that allows comparing autonomously generated behaviors with each other, and, for the first time, evaluates the human perception of IM-based generated behavior in robots. We conducted a within-subjects user study (N=24) where participants interacted with a fully autonomous Sphero BB8 robot with different behavioral regimes: one realizing an adaptive, intrinsically motivated behavior and the other being reactive, but not adaptive. The robot and its behaviors are intentionally kept minimal to concentrate on the effect induced by IM. A quantitative analysis of post-interaction questionnaires showed a significantly higher perception of the dimension "Warmth" compared to the reactive baseline behavior. Warmth is considered a primary dimension for social attitude formation in human social cognition. A human perceived as warm (friendly, trustworthy) experiences more positive social interactions.

Martin Biehl, Christian Guckelsberger, Christoph Salge et al.

Active inference is an ambitious theory that treats perception, inference and action selection of autonomous agents under the heading of a single principle. It suggests biologically plausible explanations for many cognitive phenomena, including consciousness. In active inference, action selection is driven by an objective function that evaluates possible future actions with respect to current, inferred beliefs about the world. Active inference at its core is independent from extrinsic rewards, resulting in a high level of robustness across e.g.\ different environments or agent morphologies. In the literature, paradigms that share this independence have been summarised under the notion of intrinsic motivations. In general and in contrast to active inference, these models of motivation come without a commitment to particular inference and action selection mechanisms. In this article, we study if the inference and action selection machinery of active inference can also be used by alternatives to the originally included intrinsic motivation. The perception-action loop explicitly relates inference and action selection to the environment and agent memory, and is consequently used as foundation for our analysis. We reconstruct the active inference approach, locate the original formulation within, and show how alternative intrinsic motivations can be used while keeping many of the original features intact. Furthermore, we illustrate the connection to universal reinforcement learning by means of our formalism. Active inference research may profit from comparisons of the dynamics induced by alternative intrinsic motivations. Research on intrinsic motivations may profit from an additional way to implement intrinsically motivated agents that also share the biological plausibility of active inference.

Martin Biehl, Daniel Polani

This is a contribution to the formalization of the concept of agents in multivariate Markov chains. Agents are commonly defined as entities that act, perceive, and are goal-directed. In a multivariate Markov chain (e.g. a cellular automaton) the transition matrix completely determines the dynamics. This seems to contradict the possibility of acting entities within such a system. Here we present definitions of actions and perceptions within multivariate Markov chains based on entity-sets. Entity-sets represent a largely independent choice of a set of spatiotemporal patterns that are considered as all the entities within the Markov chain. For example, the entity-set can be chosen according to operational closure conditions or complete specific integration. Importantly, the perception-action loop also induces an entity-set and is a multivariate Markov chain. We then show that our definition of actions leads to non-heteronomy and that of perceptions specialize to the usual concept of perception in the perception-action loop.

Martin Biehl, Takashi Ikegami, Daniel Polani

We present some arguments why existing methods for representing agents fall short in applications crucial to artificial life. Using a thought experiment involving a fictitious dynamical systems model of the biosphere we argue that the metabolism, motility, and the concept of counterfactual variation should be compatible with any agent representation in dynamical systems. We then propose an information-theoretic notion of \emph{integrated spatiotemporal patterns} which we believe can serve as the basic building block of an agent definition. We argue that these patterns are capable of solving the problems mentioned before. We also test this in some preliminary experiments.

Christoph Salge, Cornelius Glackin, Daniel Polani

One aspect of intelligence is the ability to restructure your own environment so that the world you live in becomes more beneficial to you. In this paper we investigate how the information-theoretic measure of agent empowerment can provide a task-independent, intrinsic motivation to restructure the world. We show how changes in embodiment and in the environment change the resulting behaviour of the agent and the artefacts left in the world. For this purpose, we introduce an approximation of the established empowerment formalism based on sparse sampling, which is simpler and significantly faster to compute for deterministic dynamics. Sparse sampling also introduces a degree of randomness into the decision making process, which turns out to beneficial for some cases. We then utilize the measure to generate agent behaviour for different agent embodiments in a Minecraft-inspired three dimensional block world. The paradigmatic results demonstrate that empowerment can be used as a suitable generic intrinsic motivation to not only generate actions in given static environments, as shown in the past, but also to modify existing environmental conditions. In doing so, the emerging strategies to modify an agent's environment turn out to be meaningful to the specific agent capabilities, i.e., de facto to its embodiment.

Christoph Salge, Daniel Polani

One of the remarkable feats of intelligent life is that it restructures the world it lives in for its own benefit. This extended abstract outlines how the information-theoretic principle of empowerment, as an intrinsic motivation, can be used to restructure the environment an agent lives in. We present a first qualitative evaluation of how an agent in a 3d-gridworld builds a staircase-like structure, which reflects the agent's embodiment.

Christoph Salge, Cornelius Glackin, Daniel Polani

This book chapter is an introduction to and an overview of the information-theoretic, task independent utility function "Empowerment", which is defined as the channel capacity between an agent's actions and an agent's sensors. It quantifies how much influence and control an agent has over the world it can perceive. This book chapter discusses the general idea behind empowerment as an intrinsic motivation and showcases several previous applications of empowerment to demonstrate how empowerment can be applied to different sensor-motor configuration, and how the same formalism can lead to different observed behaviors. Furthermore, we also present a fast approximation for empowerment in the continuous domain.

Tobias Jung, Daniel Polani

We apply kernel-based methods to solve the difficult reinforcement learning problem of 3vs2 keepaway in RoboCup simulated soccer. Key challenges in keepaway are the high-dimensionality of the state space (rendering conventional discretization-based function approximation like tilecoding infeasible), the stochasticity due to noise and multiple learning agents needing to cooperate (meaning that the exact dynamics of the environment are unknown) and real-time learning (meaning that an efficient online implementation is required). We employ the general framework of approximate policy iteration with least-squares-based policy evaluation. As underlying function approximator we consider the family of regularization networks with subset of regressors approximation. The core of our proposed solution is an efficient recursive implementation with automatic supervised selection of relevant basis functions. Simulation results indicate that the behavior learned through our approach clearly outperforms the best results obtained earlier with tilecoding by Stone et al. (2005).

Tobias Jung, Daniel Polani, Peter Stone

This paper develops generalizations of empowerment to continuous states. Empowerment is a recently introduced information-theoretic quantity motivated by hypotheses about the efficiency of the sensorimotor loop in biological organisms, but also from considerations stemming from curiosity-driven learning. Empowemerment measures, for agent-environment systems with stochastic transitions, how much influence an agent has on its environment, but only that influence that can be sensed by the agent sensors. It is an information-theoretic generalization of joint controllability (influence on environment) and observability (measurement by sensors) of the environment by the agent, both controllability and observability being usually defined in control theory as the dimensionality of the control/observation spaces. Earlier work has shown that empowerment has various interesting and relevant properties, e.g., it allows us to identify salient states using only the dynamics, and it can act as intrinsic reward without requiring an external reward. However, in this previous work empowerment was limited to the case of small-scale and discrete domains and furthermore state transition probabilities were assumed to be known. The goal of this paper is to extend empowerment to the significantly more important and relevant case of continuous vector-valued state spaces and initially unknown state transition probabilities. The continuous state space is addressed by Monte-Carlo approximation; the unknown transitions are addressed by model learning and prediction for which we apply Gaussian processes regression with iterated forecasting. In a number of well-known continuous control tasks we examine the dynamics induced by empowerment and include an application to exploration and online model learning.