Curriculum Learning with Hindsight Experience Replay for Sequential Object Manipulation Tasks

no code implementations • 21 Aug 2020 • Binyamin Manela, Armin Biess

Learning complex tasks from scratch is challenging and often impossible for humans as well as for artificial agents.

Metric-Based Imitation Learning Between Two Dissimilar Anthropomorphic Robotic Arms

no code implementations • 25 Feb 2020 • Marcus Ebner von Eschenbach, Binyamin Manela, Jan Peters, Armin Biess

The development of autonomous robotic systems that can learn from human demonstrations to imitate a desired behavior - rather than being manually programmed - has huge technological potential.

Imitation Learning Vocal Bursts Valence Prediction

Deep Reinforcement Learning for Complex Manipulation Tasks with Sparse Feedback

no code implementations • 12 Jan 2020 • Binyamin Manela

Lastly, we enable the learning of complex, sequential, tasks using a form of curriculum learning combined with HER.

Multi-Goal Reinforcement Learning reinforcement-learning +1

Bias-Reduced Hindsight Experience Replay with Virtual Goal Prioritization

1 code implementation • 14 May 2019 • Binyamin Manela, Armin Biess

We call this property the instructiveness of the virtual goal and define it by a heuristic measure, which expresses how well the agent will be able to generalize from that virtual goal to actual goals.

Multi-Goal Reinforcement Learning