Latent Actions Research Articles

Plasma-Driven Sciences: Exploring Complex Interactions at Plasma Boundaries

Plasma-driven science is defined as the artificial control of physical plasma-driven phenomena based on complex interactions between nonequilibrium open systems. Recently, peculiar phenomena related to physical plasma have been discovered in plasma boundary regions, either naturally or artificially. Because laboratory plasma can be produced under nominal conditions around atmospheric pressure and room temperature, phenomena related to the interaction of plasma with liquid solutions and living organisms at the plasma boundaries are emerging. Currently, the relationships between these complex interactions should be solved using science-based data-driven approaches; these approaches require a reliable and comprehensive database of dynamic changes in the chemical networks of elementary reactions. Consequently, the elucidation of the mechanisms governing plasma-driven phenomena and the discovery of the latent actions behind these plasma-driven phenomena will be realized through plasma-driven science.

DORA: Towards policy optimization for task-oriented dialogue system with efficient context

Recently, reinforcement learning (RL) has been applied to task-oriented dialogue systems by using latent actions to solve shortcomings of supervised learning (SL). In this paper, we propose a multi-domain task-oriented dialogue system, called Dialogue System with Optimizing a Recurrent Action Policy using Efficient Context (DORA), that uses SL, with subsequently applied RL to optimize dialogue systems using a recurrent dialogue policy. This dialogue policy recurrently generates explicit system actions as a both word-level and high-level policy. As a result, DORA is clearly optimized during both SL and RL steps by using an explicit system action policy that considers an efficient context instead of the entire dialogue history. The system actions are both interpretable and controllable, whereas the latent actions are not. DORA improved the success rate by 6.6 points on MultiWOZ 2.0 and by 10.9 points on MultiWOZ 2.1.

Learning latent actions to control assistive robots.

Assistive robot arms enable people with disabilities to conduct everyday tasks on their own. These arms are dexterous and high-dimensional; however, the interfaces people must use to control their robots are low-dimensional. Consider teleoperating a 7-DoF robot arm with a 2-DoF joystick. The robot is helping you eat dinner, and currently you want to cut a piece of tofu. Today’s robots assume a pre-defined mapping between joystick inputs and robot actions: in one mode the joystick controls the robot’s motion in the x–y plane, in another mode the joystick controls the robot’s z–yaw motion, and so on. But this mapping misses out on the task you are trying to perform! Ideally, one joystick axis should control how the robot stabs the tofu, and the other axis should control different cutting motions. Our insight is that we can achieve intuitive, user-friendly control of assistive robots by embedding the robot’s high-dimensional actions into low-dimensional and human-controllable latent actions. We divide this process into three parts. First, we explore models for learning latent actions from offline task demonstrations, and formalize the properties that latent actions should satisfy. Next, we combine learned latent actions with autonomous robot assistance to help the user reach and maintain their high-level goals. Finally, we learn a personalized alignment model between joystick inputs and latent actions. We evaluate our resulting approach in four user studies where non-disabled participants reach marshmallows, cook apple pie, cut tofu, and assemble dessert. We then test our approach with two disabled adults who leverage assistive devices on a daily basis.

Problems of the Criminal Prosecution of Persons Who Committed Actions Constitution Implication in a Crime

The paper discusses highly latent actions constituting implication in a crime. The goal of this study is to identify the problems of criminally prosecuting persons who committed actions constituting implication in a crime, to qualify them and to develop recommendations for their elimination. Formal legal and comparative legal methods were used to obtain and process results relevant for the research, the statistical method was used to collect and analyze data on the examined crimes, and the sociolo­gical one — to conduct a survey of experts. An analysis of criminal cases made it possible to state that the problem of criminally prosecuting persons who committed actions constituting implication in a crime is connected with the problems of their qualification, and with widening the institute of implication through failure to report a crime; this action is included in the Criminal Code of the Russian Federation in connection with the topical issues of terrorism threat, a growing number of terrorist crimes and the necessity to protect the society from them. The authors believe that it is reasonable to recognize 16 years old as the minimum age of criminal responsibility for failure to report a crime. It is proven that the criminal character of implication in a crime could be based not only on the guilty verdict for the main case, but also on other procedural acts. It is concluded that implication in a socially dangerous act is possible for a person who does not possess the attribute of a subject of a crime due to his/her mental incompetence, and is also possible for a crime committed in complicity. It is stated that concealment of a crime is constituted by actions to conceal the event of the main crime, its traces, the objects obtained through criminal means, or the person who committed the main crime. It can be committed not only through physical, but also through intellectual actions. The authors suggest differentiating between criminal liability for the concealment of grave and especially grave crimes. The analysis of judicial investigation practice made it possible to identify typical models of qualifying actions constituting implication in a crime, as well as psychological, moral, criminological and criminal law features of a person who conceals a crime or fails to report it. Based on the authors’ position, a formulation of the decree of the Plenary Session of the Supreme Court of the Russian Federation «On some issues of implication in a crime» is suggested.

Planning in Learned Latent Action Spaces for Generalizable Legged Locomotion

Hierarchical learning has been successful at learning generalizable locomotion skills on walking robots in a sample-efficient manner. However, the low-dimensional “latent” action used to communicate between two layers of the hierarchy is typically user-designed. In this letter, we present a fully-learned hierarchical framework, that is capable of jointly learning the low-level controller and the high-level latent action space. Once this latent space is learned, we plan over continuous latent actions in a model-predictive control fashion, using a learned high-level dynamics model. This framework generalizes to multiple robots, and we present results on a Daisy hexapod simulation, A1 quadruped simulation, and Daisy robot hardware. We compare a range of learned hierarchical approaches from literature, and show that our framework outperforms baselines on multiple tasks and two simulations. In addition to learning approaches, we also compare to inverse-kinematics (IK) acting on desired robot motion, and show that our fully-learned framework outperforms IK in adverse settings on both A1 and Daisy simulations. On hardware, we show the Daisy hexapod achieve multiple locomotion tasks, in an unstructured outdoor setting, with only 2000 hardware samples, reinforcing the robustness and sample-efficiency of our approach.

Patent Nash equilibria in symmetric strictly competitive games

This work refines the notion of Nash equilibrium in the case of symmetric strictly competitive games. We define a (complete and typically intransitive) binary relation allowing to identify the so-called latent actions, for which there exists a maximal tree whose nodes are all preferred to the considered action. We prove the existence of patent Nash equilibria (obtained after iterated elimination of latent actions) and then describe the configurations that may arise when the two players have four (or less) actions available.

INDUSTRY 4.0 AND THE CIRCULAR ECONOMY: ARE THESE INTEGRATED OR DISJOINTED CONCEPTS? A RESEARCH AGENDA

Purpose - To analyze whether the concepts of industry 4.0 and the circular economy are integrated or disjointed, recognizing which keywords are most used in the literature regarding this relationship and the occurrence. Design/methodology/approach – A bibliometric study and keyword study were used to recognize which were the most latent actions and strategies in the study of integration. The software VOSviewer was used to study the keywords.Findings - The concepts of industry 4.0 and the circular economy can be considered interconnected, with some limitations explored in the article, along with proposed future research opportunities on the subject.Originality/value - This study contributes to business managers in the sense that it facilitates an understanding that industry 4.0 and the circular economy can be used together. The result of the keywords identifies which skills, strategies, technologies and fundamentals the company should develop to make the circular economy effective, through industry 4.0. For academic research, another study has contributed to the integration of industry 4.0 and the circular economy, which is not found very often in the literature. Keywords were also mapped, which, until now, had not been developed in existing articles on integration, in addition to proposing a framework that can be transformed and suggesting research opportunities.Keywords - Industry 4.0; Circular Economy; Integration; Sustainability; Future research.

MALA: Cross-Domain Dialogue Generation with Action Learning

Response generation for task-oriented dialogues involves two basic components: dialogue planning and surface realization. These two components, however, have a discrepancy in their objectives, i.e., task completion and language quality. To deal with such discrepancy, conditioned response generation has been introduced where the generation process is factorized into action decision and language generation via explicit action representations. To obtain action representations, recent studies learn latent actions in an unsupervised manner based on the utterance lexical similarity. Such an action learning approach is prone to diversities of language surfaces, which may impinge task completion and language quality. To address this issue, we propose multi-stage adaptive latent action learning (MALA) that learns semantic latent actions by distinguishing the effects of utterances on dialogue progress. We model the utterance effect using the transition of dialogue states caused by the utterance and develop a semantic similarity measurement that estimates whether utterances have similar effects. For learning semantic actions on domains without dialogue states, MALA extends the semantic similarity measurement across domains progressively, i.e., from aligning shared actions to learning domain-specific actions. Experiments using multi-domain datasets, SMD and MultiWOZ, show that our proposed model achieves consistent improvements over the baselines models in terms of both task completion and language quality.

Learning Hidden Human Context in 3D Office Scenes by Mapping Affordances Through Virtual Humans

Ability to learn human context in an environment could be one of the most desired fundamental abilities that a robot should have when sharing a workspace with human co-workers. Arguably, a robot with appropriate human context awareness could lead to a better human–robot interaction. In this paper, we address the problem of learning human context in an office environment by only using 3D point cloud data. Our approach is based on the concept of affordance-map, which involves mapping latent human actions in a given environment by looking at geometric features of the environment. This enables us to learn the human context in the environment without observing real human behaviors which themselves are a nontrivial task to detect. Once learned, affordance-map allows us to assign an affordance cost value for each grid location of the map. These cost maps are later used to develop an active object search strategy and to develop a context-aware global path planning strategy.

“You Are a Racist”: An Early Childhood Educator's Racialized Awakening

This article details my racialized awakenings as a White kindergarten teacher after being called a racist by a parent of one of my students. I chronicle critical reflections of myself and my school in terms of latent institutional racism and actions. I share the actions that I have begun in my efforts to counter racism and move toward teaching for social justice. Changes in my teaching included interrupting deficit perspectives, talking explicitly about race, critiquing literature that I use in my classroom, and exploring ways to provide ongoing counternarratives that honor culturally and linguistically diverse students. I conclude with implications for other Early Childhood teachers who are teaching across racial boundaries. While I do not position my findings as the solution to countering institutional racism in the classroom, I hope that my journey can be enlightening to educators facing similar conflicts.

Pathological growth of androgen‐sensitive tissues resulting from latent actions of steroid hormones

Hormonal responsiveness should be considered in terms of at least three homeostatic constraint mechanisms. Observations on the induction of specific responses in rat prostate reveal that certain of these are controlled differentially, and also that immature cells can be modified by low levels of androgen. The conditioning effect of low levels of steroid is further demonstrated by the benefits of fractional hormone-replacement therapy in controlling and delaying tumor progression. A revised approach to endocrine therapy of cancer should be seriously considered. This would entail the fractional replacement of hormone after ablative surgery.