Time Limits in Reinforcement Learning — mentioned by jimfleming

Tue, 12 Feb 2019 20:09:40 GMT

Hopefully this leads to better temporal priors for machine learning models. Sequence encoding frequently uses position coding[0] but the typical approaches (e.g. low frequency sin waves) are fairly naive. In reinforcement learning we have (somewhat obvious) works that show that providing explicit time representations help[1]. Simply throwing a recurrent model at a sequence may pick up simple ordering but improving the temporal representation would improve data efficiency. [0] https://arxiv.org/abs/1706.03762 [1] https://arxiv.org/abs/1712.00378

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

Time Limits in Reinforcement Learning · HackerPapers discussions

Time Limits in Reinforcement Learning — mentioned by jimfleming