Reinforcement Learning with Unsupervised Auxiliary Tasks · HackerPapers discussions

Reinforcement Learning with Unsupervised Auxiliary Tasks — mentioned by sapphireblue

Mon, 05 Dec 2016 14:38:56 GMT

Looks like the "UNREAL" (https://arxiv.org/abs/1611.05397), "Learning to reinforcement learn" (https://arxiv.org/abs/1611.05763) and "RL^2" (https://arxiv.org/abs/1611.02779) are state of art in pure RL for now. Finally there is a trend of using recurrent neural network as a top component of the Q-network. Perhaps we will see even more sophisticated RNNs like DNC and Recurrent Entity Networks applied here. Also we'll see meta-reinforcement learning applied to a curriculum of environments.

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

Reinforcement Learning with Unsupervised Auxiliary Tasks — HN submission

Thu, 17 Nov 2016 15:49:03 GMT

Reinforcement Learning with Unsupervised Auxiliary Tasks

47 points; 6 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Reinforcement Learning with Unsupervised Auxiliary Tasks — HN submission

Thu, 17 Nov 2016 06:29:15 GMT

Reinforcement Learning with Unsupervised Auxiliary Tasks

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.