United Kingdom

We study perception in the scenario of an embodied agent equipped with first-person sensors and a continuous motor space with multiple degrees of freedom. We consider the commutative properties of action sequences with respect to sensory information perceived by such an embodied agent. We introduce the Sensory Commutativity Probability (SCP) criterion which measures how much an agent&#39;s degree of freedom affects the environment in embodied scenarios. We show how to compute this criterion in different environments, including realistic robotic setups and discuss how SCP and the commutative properties of action sequences can be used to learn about objects in the environment and improve sample-efficiency in Reinforcement Learning.

AAMAS 2021

On the Sensory Commutativity of Action Sequences for Embodied Agents

AAMAS is the largest and most influential conference in the area of agents and multiagent systems, bringing together researchers and practitioners in all areas of agent technology and providing and internationally renowned high-profile forum for publishing and finding out about the latest developments in the field. AAMAS is the flagship conference of the non-profit International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS).  

![](https://s3.eu-west-1.amazonaws.com/underline.prod/uploads/markdown_image/1/image/ce4604bd54468a006164d16e080204fb.jpg)

Please click on the button below to register for this event.

If you are registered and see this page please check the account email you are logged in with. It must be the same as for the registration.

If you still have trouble accessing the contact please contact support at aamas2021@underline.io 

EMNLP 2021 is planned to be a hybrid event in Punta Cana, Dominican Republic, with both on-site and fully virtual participation possible. The experience for on-site participants would closely approximate a normal pre-COVID *ACL conference, with 5-6 thematically organized parallel sessions and live Q/A and interactive discussion immediately after the talks. Presentations by virtual participants will be equitably interleaved with those of on-site participants, projected on the auditorium screens as if on-site, and also followed immediately by live Q/A and interactive discussion at a time during reasonable waking hours for the virtual presenter. For all participants, on-site and virtual, who are unable to attend a session due to either time-zone issues or because they are participating in another session live, talk recordings and slides will be available online at a minimum after the live presentation (and in many cases before as well), and questions may be submitted in advance on session-specific discussion boards and answered live in session with the usual visual aids if desired.

<iframe style="width:700px;height:400px" src="https://online.fliphtml5.com/ebtyf/ceby/"  seamless="seamless" scrolling="no" frameborder="0" allowtransparency="true" allowfullscreen="true" ></iframe>

Please Note: The EMNLP registration system is not currently connected to the underline site as we are still in the process of building out EMNLP 2021. You will receive access instructions from underline the week of November 1st. 

Access is given only to EMNLP upon registration, if you have not registered please do so [here](https://2021.emnlp.org/registration).

Registered attendees will receive access the week of November 1st.

EMNLP 2021

EMNLP 2021 is planned to be a hybrid event in Punta Cana, Dominican Republic, with both on-site and fully virtual participation possible.

We study perception in the scenario of an embodied agent equipped with first-person sensors and a continuous motor space with multiple degrees of freedom. We consider the commutative properties of action sequences with respect to sensory information perceived by such an embodied agent. We introduce the Sensory Commutativity Probability (SCP) criterion which measures how much an agent's degree of freedom affects the environment in embodied scenarios. We show how to compute this criterion in different environments, including realistic robotic setups and discuss how SCP and the commutative properties of action sequences can be used to learn about objects in the environment and improve sample-efficiency in Reinforcement Learning.

poster

This paper describes a demonstration setup that integrates cognitive agents with the latest W3C standardization efforts for the Web of Things (WoT). The conceptual foundations of the implemented system are the integration of cognitive agent abstractions with W3C Web Things, which are generic abstractions of devices and virtual services that provide agents with various interaction affordances (e.g., actions, events). Together with the W3C WoT Scripting API, which is an ECMAScript-compatible API for W3C WoT environments, these standards allow JavaScript-based agents to be deployed and to operate in heterogeneous WoT environments. The agents can then be effectively distributed across the physical-virtual space in a write once, run anywhere manner: we deploy agents across a heterogeneous information system landscape that includes Web servers, browser-based front-ends, and constrained devices (microcontrollers). The deployment only requires minor platform-specific adjustments to consider resource and performance limitations on constrained devices. As a running example, we demonstrate a semi-autonomous assembly scenario with human-in-the-loop support.

Autonomous Agents on the Edge of Things

We investigate a problem that lies at the intersection of three research areas, namely Automated Negotiation, Vehicle Routing, and Multi-Objective Optimization. Specifically, we investigate the scenario that multiple competing logistics companies aim to cooperate by delivering truck loads for one another, in order to improve efficiency and reduce the distance they drive. In order to do so, these companies need to find ways to exchange their truck loads such that each of them individually benefits. We present a new heuristic algorithm that, given one set of orders to deliver for each company, tries to find the set of all order-exchanges that are Pareto-optimal and individually rational. Furthermore, we present experiments based on real-world test data from two major logistics companies, which show that our algorithm is able to find hundreds of solutions in a matter of minutes.

A Heuristic Algorithm for Multi-Agent Vehicle Routing with Automated Negotiation

Although reinforcement learning has been successfully applied in many domains in recent years, we still lack agents that can systematically generalize. While relational inductive biases that fit a task can improve generalization of RL agents, these biases are commonly hard-coded directly in the agent's neural architecture. In this work, we show that we can incorporate relational inductive biases, encoded in the form of relational graphs, into agents. Based on this insight, we propose Grid-to-Graph (GTG), a mapping from grid structures to relational graphs that carry useful spatial relational inductive biases when processed through a Relational Graph Convolution Network (R-GCN). We show that, with GTG, R-GCNs generalize better both in terms of in-distribution and out-of-distribution compared to baselines based on Convolutional Neural Networks and Neural Logic Machines on challenging procedurally generated environments and MinAtar. Furthermore, we show that GTG produces agents that can jointly reason over observations and environment dynamics encoded in knowledge bases.

Grid-to-Graph: Flexible Spatial Relational Inductive Biases for Reinforcement Learning

Solving the Multi-Agent Path Finding (MAPF) problem optimally is known to be NP-Hard for both make-span and total arrival time minimization. While many algorithms have been developed to solve MAPF problems, there is no dominating optimal MAPF algorithm that works well in all types of problems and no standard guidelines for when to use which algorithm. In this work, we develop the deep convolutional network MAPFAST (Multi-Agent Path Finding Algorithm SelecTor), which takes a MAPF problem instance and attempts to select the fastest algorithm to use from a portfolio of algorithms. We improve the performance of our model by including single-agent shortest paths in the instance embedding given to our model and by utilizing supplemental loss functions in addition to a classification loss. We evaluate our model on a large and diverse dataset of MAPF instances, showing that it outperforms all individual algorithms in its portfolio as well as the state-of-the-art optimal MAPF algorithm selector. We also provide an analysis of algorithm behavior in our dataset to gain a deeper understanding of optimal MAPF algorithms' strengths and weaknesses to help other researchers leverage different heuristics in algorithm designs.

MAPFAST: A Deep Algorithm Selector for Multi Agent Path Finding using Shortest Path Embeddings

Despite abundant negotiation strategies in literature, the complexity of automated negotiation forbids a single strategy from being dominant against all others in different negotiation scenarios. To overcome this, one approach is to use mixture of experts, but at the same time, one problem of this method is the selection of experts, as this approach is limited by the competency of the experts selected. Another problem with most negotiation strategies is their incapability of adapting to dynamic variation of the opponent's behaviour within a single negotiation session resulting in poor performance. This work focuses on both, solving the problem of expert selection and adapting to the opponent's behaviour with our Autonomous Negotiating Agent Framework. This framework allows real-time classification of opponent's behaviour and provides a mechanism to select, switch or combine strategies within a single negotiation session. Additionally, our framework has a reviewer component which enables self-enhancement capability by deciding to include new strategies or replace old ones with better strategies periodically. We demonstrate an instance of our framework by implementing maximum entropy reinforcement learning based strategies with a deep learning based opponent classifier. Finally, we evaluate the performance of our agent against state-of-the-art negotiators under varied negotiation scenarios.

An Autonomous Negotiating Agent Framework with Reinforcement Learning based Strategies and Adaptive Strategy Switching Mechanism

The classical 'buy or rent' ski-rental problem was recently considered in the setting where multiple experts (such as Machine learning algorithms) advice on the length of the ski season. Here, robust algorithms were developed with improved theoretical performance over adversarial scenarios where such expert predictions were unavailable. We consider a variant of this problem which we call the 'sequential ski-rental' problem. Here, a sequence of ski-rental problems has to be solved in an online fashion where both the buy cost and the length of ski season are unknown to the learner. The learner has access to two sets of experts, one set who advise on the true cost of buying the ski and another set who advise on the length of the ski season. Under certain stochastic assumptions on the experts who predict the buy costs, we develop online algorithms and prove regret bounds for the same. Our experimental evaluations confirm our theoretical results.

Sequential Ski Rental Problem

We present an extension of the organizational model and infrastructure adopted in JaCaMo, that explicitly encompasses the notion of exception. We propose an exception handling mechanism for organization management in multi-agent systems. This mechanism relies on abstractions that are seamlessly integrated with organizational concepts, such as responsibilities, goals and norms.

Distributing Responsibilities for Exception Handling in JaCaMo

Value alignment is a crucial aspect of ethical multiagent systems. An important step toward value alignment is identifying values specific to an application context. However, identifying context-specific values is complex and cognitively demanding. To support this process, we develop a methodology and a collaborative web platform that employs AI techniques. We describe this platform, highlighting its intuitive design and implementation.

A Collaborative Platform for Identifying Context-Specific Values

Participatory Budgeting processes are usually designed to span several years, with referenda for new budget allocations taking place regularly. This paper presents the first formalization of long-term PB. We introduce a theory of fairness for this setting, investigate under which conditions our fairness criteria can be satisfied, and analyze the computational complexity of verifying them.

Fairness in Long-Term Participatory Budgeting

Most frameworks for computing solution concepts in hedonic games are theoretical in nature, and require complete knowledge of all agent preferences, an impractical assumption in real-world settings. This paper presents the first application of strategic hedonic game models on real-world data. We show that PAC stable solutions can reflect Members of Knesset' political positions and reveal politicians who are known to deviate from party lines. Moreover, these models compare favorably to machine learning models.

On the Sensory Commutativity of Action Sequences for Embodied Agents

Next from AAMAS 2021

Autonomous Agents on the Edge of Things

Similar lecture

Analyzing the Surprising Variability in Word Embedding Stability Across Languages

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES