21 citations · 118 across the 15 of their papers we have counts for
9 papers · 1 filter
Continual Deep Reinforcement Learning with Task-Agnostic Policy Distillation
Muhammad Burhan Hafez, Kerim Erekmen
Central to the development of universal learning systems is the ability to solve multiple tasks without retraining from scratch when new data arrives. This is crucial because each…
QT-TDM: Planning With Transformer Dynamics Model and Autoregressive Q-Learning
Mostafa Kotb, Cornelius Weber, Muhammad Burhan Hafez +1
Inspired by the success of the Transformer architecture in natural language processing and computer vision, we investigate the use of Transformers in Reinforcement Learning (RL), s…
Map-based Experience Replay: A Memory-Efficient Solution to Catastrophic Forgetting in Reinforcement Learning
Muhammad Burhan Hafez, Tilman Immisch, Tom Weber +1
Deep Reinforcement Learning agents often suffer from catastrophic forgetting, forgetting previously found solutions in parts of the input space when training on new data. Replay Me…
Model Predictive Control with Self-supervised Representation Learning
Jonas Matthies, Muhammad Burhan Hafez, Mostafa Kotb +1
Over the last few years, we have not seen any major developments in model-free or model-based learning methods that would make one obsolete relative to the other. In most cases, th…
Improving Model-Based Reinforcement Learning with Internal State Representations through Self-Supervision
Julien Scholz, Cornelius Weber, Muhammad Burhan Hafez +1
Using a model of the environment, reinforcement learning agents can plan their future moves and achieve superhuman performance in board games like Chess, Shogi, and Go, while remai…
Improving Robot Dual-System Motor Learning with Intrinsically Motivated Meta-Control and Latent-Space Experience Imagination
Muhammad Burhan Hafez, Cornelius Weber, Matthias Kerzel +1
Combining model-based and model-free learning systems has been shown to improve the sample efficiency of learning to perform complex robotic tasks. However, dual-system approaches…
Efficient Intrinsically Motivated Robotic Grasping with Learning-Adaptive Imagination in Latent Space
Muhammad Burhan Hafez, Cornelius Weber, Matthias Kerzel +1
Combining model-based and model-free deep reinforcement learning has shown great promise for improving sample efficiency on complex control tasks while still retaining high perform…
Curious Meta-Controller: Adaptive Alternation between Model-Based and Model-Free Control in Deep Reinforcement Learning
Muhammad Burhan Hafez, Cornelius Weber, Matthias Kerzel +1
Recent success in deep reinforcement learning for continuous control has been dominated by model-free approaches which, unlike model-based approaches, do not suffer from representa…
Deep Intrinsically Motivated Continuous Actor-Critic for Efficient Robotic Visuomotor Skill Learning
Muhammad Burhan Hafez, Cornelius Weber, Matthias Kerzel +1
In this paper, we present a new intrinsically motivated actor-critic algorithm for learning continuous motor skills directly from raw visual input. Our neural architecture is compo…