research
∙
09/26/2022
Overcoming Referential Ambiguity in Language-Guided Goal-Conditioned Reinforcement Learning
Teaching an agent to perform new tasks using natural language can easily...
share
research
∙
06/09/2022
Pragmatically Learning from Pedagogical Demonstrations in Multi-Goal Environments
Learning from demonstration methods usually leverage close to optimal de...
research
∙
02/28/2022
Pedagogical Demonstrations and Pragmatic Learning in Artificial Tutor-Learner Interactions
When demonstrating a task, human tutors pedagogically modify their behav...
research
∙
07/05/2021
Are standard Object Segmentation models sufficient for Learning Affordance Segmentation?
Affordances are the possibilities of actions the environment offers to t...
research
∙
07/05/2021
SCOD: Active Object Detection for Embodied Agents using Sensory Commutativity of Action Sequences
We introduce SCOD (Sensory Commutativity Object Detection), an active me...
research
∙
05/25/2021
Towards Teachable Autonomous Agents
Autonomous discovery and direct instruction are two extreme sources of l...
research
∙
02/13/2020
On the Sensory Commutativity of Action Sequences for Embodied Agents
We study perception in the scenario of an embodied agent equipped with f...
research
∙
07/11/2019
DisCoRL: Continual Reinforcement Learning via Policy Distillation
In multi-task reinforcement learning there are two main challenges: at t...
research
∙
06/11/2019
Continual Reinforcement Learning deployed in Real-life using Policy Distillation and Sim2Real Transfer
We focus on the problem of teaching a robot to solve tasks presented seq...
research
∙
03/30/2019
Symmetry-Based Disentangled Representation Learning requires Interaction with Environments
Finding a generally accepted formal definition of a disentangled represe...
research
∙
02/25/2019
S-TRIGGER: Continual State Representation Learning via Self-Triggered Generative Replay
We consider the problem of building a state representation model for con...
research
∙
12/21/2018
Generative Models from the perspective of Continual Learning
Which generative model is the most suitable for Continual Learning? This...
research
∙
10/09/2018
Continual State Representation Learning for Reinforcement Learning using Generative Replay
We consider the problem of building a state representation model in a co...
research
∙
09/03/2018
Flatland: a Lightweight First-Person 2-D Environment for Reinforcement Learning
We propose Flatland, a simple, lightweight environment for fast prototyp...
research
∙
04/11/2018