22 citations · 47 across the 12 of their papers we have counts for
14 papers
Imitating Language via Scalable Inverse Reinforcement Learning
Markus Wulfmeier, Michael Bloesch, Nino Vieillard +13
The majority of language model training builds on imitation learning. It covers pretraining, supervised fine-tuning, and affects the starting conditions for reinforcement learning…
Genie: Generative Interactive Environments
Jake Bruce, Michael Dennis, Ashley Edwards +22
We introduce Genie, the first generative interactive environment trained in an unsupervised manner from unlabelled Internet videos. The model can be prompted to generate an endless…
Offline Actor-Critic Reinforcement Learning Scales to Large Models
Jost Tobias Springenberg, Abbas Abdolmaleki, Jingwei Zhang +9
We show that offline actor-critic reinforcement learning can scale to large models - such as transformers - and follows similar scaling laws as supervised learning. We find that of…
Mastering Stacking of Diverse Shapes with Large-Scale Iterative Reinforcement Learning on Real Robots
Thomas Lampe, Abbas Abdolmaleki, Sarah Bechtle +12
Reinforcement learning solely from an agent's self-generated data is often believed to be infeasible for learning on real robots, due to the amount of data needed. However, if done…
Foundations for Transfer in Reinforcement Learning: A Taxonomy of Knowledge Modalities
Markus Wulfmeier, Arunkumar Byravan, Sarah Bechtle +2
Contemporary artificial intelligence systems exhibit rapidly growing abilities accompanied by the growth of required resources, expansive datasets and corresponding investments int…
Equivariant Data Augmentation for Generalization in Offline Reinforcement Learning
Cristina Pinneri, Sarah Bechtle, Markus Wulfmeier +4
We present a novel approach to address the challenge of generalization in offline reinforcement learning (RL), where the agent learns from a fixed dataset without any additional in…
A Generalist Dynamics Model for Control
Ingmar Schubert, Jingwei Zhang, Jake Bruce +7
We investigate the use of transformer sequence models as dynamics models (TDMs) for control. We find that TDMs exhibit strong generalization capabilities to unseen environments, bo…
Model Based Meta Learning of Critics for Policy Gradients
Sarah Bechtle, Ludovic Righetti, Franziska Meier
Being able to seamlessly generalize across different tasks is fundamental for robots to act in our world. However, learning representations that generalize quickly to new scenarios…
Learning Time-Invariant Reward Functions through Model-Based Inverse Reinforcement Learning
Todor Davchev, Sarah Bechtle, Subramanian Ramamoorthy +1
Inverse reinforcement learning is a paradigm motivated by the goal of learning general reward functions from demonstrated behaviours. Yet the notion of generality for learnt costs…
Leveraging Forward Model Prediction Error for Learning Control
Sarah Bechtle, Bilal Hammoud, Akshara Rai +2
Learning for model based control can be sample-efficient and generalize well, however successfully learning models and controllers that represent the problem at hand can be challen…
Multi-Modal Learning of Keypoint Predictive Models for Visual Object Manipulation
Sarah Bechtle, Neha Das, Franziska Meier
Humans have impressive generalization capabilities when it comes to manipulating objects and tools in completely novel environments. These capabilities are, at least partially, a r…
Model-Based Inverse Reinforcement Learning from Visual Demonstrations
Neha Das, Sarah Bechtle, Todor Davchev +3
Scaling model-based inverse reinforcement learning (IRL) to real robotic manipulation tasks with unknown dynamics remains an open problem. The key challenges lie in learning good d…
Meta-Learning via Learned Loss
Sarah Bechtle, Artem Molchanov, Yevgen Chebotar +4
Typically, loss functions, regularization mechanisms and other important aspects of training parametric models are chosen heuristically from a limited set of options. In this paper…
Curious iLQR: Resolving Uncertainty in Model-based RL
Sarah Bechtle, Yixin Lin, Akshara Rai +2
Curiosity as a means to explore during reinforcement learning problems has recently become very popular. However, very little progress has been made in utilizing curiosity for lear…