Towards Generalization and Simplicity in Continuous Control — mentioned by klowrey

Thu, 21 Dec 2017 21:02:19 GMT

https://arxiv.org/abs/1703.02660 Disclosure: I contributed to the linked work. To do simple tasks, you don’t even need neural networks, in short. If you want to do complex tasks, training the neural net isn’t the problem, but a NN can indeed represent more than say a linear policy. The issue is getting the NN to do the complex thing correctly: it’s more of an exploration problem than function approximation problem.

Paper and discussion history. A mention is not an endorsement.

Towards Generalization and Simplicity in Continuous Control · HackerPapers discussions

Towards Generalization and Simplicity in Continuous Control — mentioned by klowrey