no code implementations • 12 Nov 2020 • 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.
no code implementations • 17 Jun 2019 • Adeel Mufti, Svetlin Penkov, Subramanian Ramamoorthy
The agent improves its policy in simulations generated by the DNC model and rolls out the policy to the live environment, collecting experiences in new portions or tasks of the environment for further learning.
Model-based Reinforcement Learning reinforcement-learning +1
no code implementations • ICLR 2019 • 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 extracting symbols from raw observation data and ii) a task encoding program which maps the input symbols to output actions.
no code implementations • 27 Feb 2019 • Michael Burke, Svetlin Penkov, Subramanian Ramamoorthy
This work introduces an approach to learning hybrid systems from demonstrations, with an emphasis on extracting models that are explicitly verifiable and easily interpreted by robot operators.
no code implementations • 26 Jul 2017 • 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 the formulation of more robust predictions.
no code implementations • WS 2017 • Yordan Hristov, Svetlin Penkov, Alex Lascarides, Subramanian Ramamoorthy
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 symbols in the physical world.
no code implementations • 23 May 2017 • 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 the formulation of more robust predictions.