11 citations · 22 across the 6 of their papers we have counts for
8 papers
Neural Abstract Reasoner
Victor Kolev, Bogdan Georgiev, Svetlin Penkov
Abstract reasoning and logic inference are difficult problems for neural networks, yet essential to their applicability in highly structured domains. In this work we demonstrate th…
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…
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…
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…
FPR -- Fast Path Risk Algorithm to Evaluate Collision Probability
Andrew Blake, Alejandro Bordallo, Kamen Brestnichki +4
As mobile robots and autonomous vehicles become increasingly prevalent in human-centred environments, there is a need to control the risk of collision. Perceptual modules, for exam…
Using Program Induction to Interpret Transition System Dynamics
Svetlin Penkov, Subramanian Ramamoorthy
Explaining and reasoning about processes which underlie observed black-box phenomena enables the discovery of causal mechanisms, derivation of suitable abstract representations and…
Grounding Symbols in Multi-Modal Instructions
Yordan Hristov, Svetlin Penkov, Alex Lascarides +1
As robots begin to cohabit with humans in semi-structured environments, the need arises to understand instructions involving rich variability---for instance, learning to ground sym…
Explaining Transition Systems through Program Induction
Svetlin Penkov, Subramanian Ramamoorthy
Explaining and reasoning about processes which underlie observed black-box phenomena enables the discovery of causal mechanisms, derivation of suitable abstract representations and…