66 citations · 177 across the 9 of their papers we have counts for
Showing 2020Show all
2 papers · 1 filter
cs.LG2020★ 7 cited
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…
cs.RO2020★ 13 cited
Learning Dexterous Manipulation from Suboptimal Experts
Rae Jeong, Jost Tobias Springenberg, Jackie Kay +5
Learning dexterous manipulation in high-dimensional state-action spaces is an important open challenge with exploration presenting a major bottleneck. Although in many cases the le…