Reinforcement learning for optimal control of arm movements

By Evangelos A. Theodorou, Jan Peters, Stefan Schaal. 2007

5 citations recorded by the source corpus.

Citations in the corpus

• Active learning of inverse models with intrinsically motivated goal exploration in robots (2013, neutral): “This is typically what happens in the reinforcement learning (RL) framework where no demonstration is originally required and only a goal has to be fixed (as a reward) by the engineer who conceives the system [10–12].”