254 citations · 456 across the 11 of their papers we have counts for
6 papers · 1 filter
Shaking the foundations: delusions in sequence models for interaction and control
Pedro A. Ortega, Markus Kunesch, Grégoire Delétang +16
The recent phenomenal success of language models has reinvigorated machine learning research, and large sequence models such as transformers are being applied to a variety of domai…
Local Search for Policy Iteration in Continuous Control
Jost Tobias Springenberg, Nicolas Heess, Daniel Mankowitz +10
We present an algorithm for local, regularized, policy improvement in reinforcement learning (RL) that allows us to formulate model-based and model-free variants in a single framew…
Quinoa: a Q-function You Infer Normalized Over Actions
Jonas Degrave, Abbas Abdolmaleki, Jost Tobias Springenberg +2
We present an algorithm for learning an approximate action-value soft Q-function in the relative entropy regularised reinforcement learning setting, for which an optimal improved p…
Self-supervised Learning of Image Embedding for Continuous Control
Carlos Florensa, Jonas Degrave, Nicolas Heess +2
Operating directly from raw high dimensional sensory inputs like images is still a challenge for robotic control. Recently, Reinforcement Learning methods have been proposed to sol…
Relative Entropy Regularized Policy Iteration
Abbas Abdolmaleki, Jost Tobias Springenberg, Jonas Degrave +5
We present an off-policy actor-critic algorithm for Reinforcement Learning (RL) that combines ideas from gradient-free optimization via stochastic search with learned action-value…
Learning by Playing - Solving Sparse Reward Tasks from Scratch
Martin Riedmiller, Roland Hafner, Thomas Lampe +6
We propose Scheduled Auxiliary Control (SAC-X), a new learning paradigm in the context of Reinforcement Learning (RL). SAC-X enables learning of complex behaviors - from scratch -…