10.1k citations · 10.9k across the 10 of their papers we have counts for
Showing 2015 · cs.LGShow all
2 papers · 2 filters
cs.LG2015★ 212 cited
Memory-based control with recurrent neural networks
Nicolas Heess, Jonathan J Hunt, Timothy P Lillicrap +1
Partially observed control problems are a challenging aspect of reinforcement learning. We extend two related, model-free algorithms for continuous control -- deterministic policy…
cs.LG2015★ 10.1k cited
Continuous control with deep reinforcement learning
Timothy P. Lillicrap, Jonathan J. Hunt, Alexander Pritzel +5
We adapt the ideas underlying the success of Deep Q-Learning to the continuous action domain. We present an actor-critic, model-free algorithm based on the deterministic policy gra…