59 citations · 457 across the 92 of their papers we have counts for
24 papers · 1 filter
Lower Dimensional Kernels for Video Discriminators
Emmanuel Kahembwe, Subramanian Ramamoorthy
This work presents an analysis of the discriminators used in Generative Adversarial Networks (GANs) for Video. We show that unconstrained video discriminator architectures induce a…
Learning Structured Representations of Spatial and Interactive Dynamics for Trajectory Prediction in Crowded Scenes
Todor Davchev, Michael Burke, Subramanian Ramamoorthy
Context plays a significant role in the generation of motion for dynamic agents in interactive environments. This work proposes a modular method that utilises a learned model of th…
Surfing on an uncertain edge: Precision cutting of soft tissue using torque-based medium classification
Artūras Straižys, Michael Burke, Subramanian Ramamoorthy
Precision cutting of soft-tissue remains a challenging problem in robotics, due to the complex and unpredictable mechanical behaviour of tissue under manipulation. Here, we conside…
E-HBA: Using Action Policies for Expert Advice and Agent Typification
Stefano V. Albrecht, Jacob W. Crandall, Subramanian Ramamoorthy
Past research has studied two approaches to utilise predefined policy sets in repeated interactions: as experts, to dictate our own actions, and as types, to characterise the behav…
Comparative Evaluation of Multiagent Learning Algorithms in a Diverse Set of Ad Hoc Team Problems
Stefano V. Albrecht, Subramanian Ramamoorthy
This paper is concerned with evaluating different multiagent learning (MAL) algorithms in problems where individual agents may be heterogenous, in the sense of utilizing different…
On Convergence and Optimality of Best-Response Learning with Policy Types in Multiagent Systems
Stefano V. Albrecht, Subramanian Ramamoorthy
While many multiagent algorithms are designed for homogeneous systems (i.e. all agents are identical), there are important applications which require an agent to coordinate its act…
Exploiting Causality for Selective Belief Filtering in Dynamic Bayesian Networks (Extended Abstract)
Stefano V. Albrecht, Subramanian Ramamoorthy
Dynamic Bayesian networks (DBNs) are a general model for stochastic processes with partially observed states. Belief filtering in DBNs is the task of inferring the belief state (i.…
An Empirical Study on the Practical Impact of Prior Beliefs over Policy Types
Stefano V. Albrecht, Jacob W. Crandall, Subramanian Ramamoorthy
Many multiagent applications require an agent to learn quickly how to interact with previously unknown other agents. To address this problem, researchers have studied learning algo…
Are You Doing What I Think You Are Doing? Criticising Uncertain Agent Models
Stefano V. Albrecht, S. Ramamoorthy
The key for effective interaction in many multiagent applications is to reason explicitly about the behaviour of other agents, in the form of a hypothesised behaviour. While there…
Disentangled Relational Representations for Explaining and Learning from Demonstration
Yordan Hristov, Daniel Angelov, Michael Burke +2
Learning from demonstration is an effective method for human users to instruct desired robot behaviour. However, for most non-trivial tasks of practical interest, efficient learnin…
Composing Diverse Policies for Temporally Extended Tasks
Daniel Angelov, Yordan Hristov, Michael Burke +1
Robot control policies for temporally extended and sequenced tasks are often characterized by discontinuous switches between different local dynamics. These change-points are often…
Vid2Param: Modelling of Dynamics Parameters from Video
Martin Asenov, Michael Burke, Daniel Angelov +3
Videos provide a rich source of information, but it is generally hard to extract dynamical parameters of interest. Inferring those parameters from a video stream would be beneficia…
Hybrid system identification using switching density networks
Michael Burke, Yordan Hristov, Subramanian Ramamoorthy
Behaviour cloning is a commonly used strategy for imitation learning and can be extremely effective in constrained domains. However, in cases where the dynamics of an environment m…
DynoPlan: Combining Motion Planning and Deep Neural Network based Controllers for Safe HRL
Daniel Angelov, Yordan Hristov, Subramanian Ramamoorthy
Many realistic robotics tasks are best solved compositionally, through control architectures that sequentially invoke primitives and achieve error correction through the use of loo…
Learning Grasp Affordance Reasoning through Semantic Relations
Paola Ardón, Èric Pairet, Ronald P. A. Petrick +2
Reasoning about object affordances allows an autonomous agent to perform generalised manipulation tasks among object instances. While current approaches to grasp affordance estimat…
Iterative Model-Based Reinforcement Learning Using Simulations in the Differentiable Neural Computer
Adeel Mufti, Svetlin Penkov, Subramanian Ramamoorthy
We propose a lifelong learning architecture, the Neural Computer Agent (NCA), where a Reinforcement Learning agent is paired with a predictive model of the environment learned by a…
An Empirical Evaluation of Adversarial Robustness under Transfer Learning
Todor Davchev, Timos Korres, Stathi Fotiadis +2
In this work, we evaluate adversarial robustness in the context of transfer learning from a source trained on CIFAR 100 to a target network trained on CIFAR 10. Specifically, we st…
Reasoning on Grasp-Action Affordances
Paola Ardón, Èric Pairet, Ron Petrick +2
Artificial intelligence is essential to succeed in challenging activities that involve dynamic environments, such as object manipulation tasks in indoor scenes. Most of the state-o…
Learning Programmatically Structured Representations with Perceptor Gradients
Svetlin Penkov, Subramanian Ramamoorthy
We present the perceptor gradients algorithm -- a novel approach to learning symbolic representations based on the idea of decomposing an agent's policy into i) a perceptor network…
To Stir or Not to Stir: Online Estimation of Liquid Properties for Pouring Actions
Tatiana Lopez-Guevara, Rita Pucci, Nicholas Taylor +3
Our brains are able to exploit coarse physical models of fluids to solve everyday manipulation tasks. There has been considerable interest in developing such a capability in robots…
Using Causal Analysis to Learn Specifications from Task Demonstrations
Daniel Angelov, Yordan Hristov, Subramanian Ramamoorthy
Learning models of user behaviour is an important problem that is broadly applicable across many application domains requiring human-robot interaction. In this work we show that it…
Learning Best Response Strategies for Agents in Ad Exchanges
Stavros Gerakaris, Subramanian Ramamoorthy
Ad exchanges are widely used in platforms for online display advertising. Autonomous agents operating in these exchanges must learn policies for interacting profitably with a diver…
From explanation to synthesis: Compositional program induction for learning from demonstration
Michael Burke, Svetlin Penkov, Subramanian Ramamoorthy
Hybrid systems are a compact and natural mechanism with which to address problems in robotics. This work introduces an approach to learning hybrid systems from demonstrations, with…
Active Localization of Gas Leaks using Fluid Simulation
Martin Asenov, Marius Rutkauskas, Derryck Reid +2
Sensors are routinely mounted on robots to acquire various forms of measurements in spatio-temporal fields. Locating features within these fields and reconstruction (mapping) of th…