A DRL-Based Container Placement Scheme with Auxiliary Tasks

Reinforcement Learning with Unsupervised Auxiliary Tasks

Deep reinforcement learning agents have achieved state-of-the-art results by directly maximising cumulative reward. However, environments contain a much wider variety of possible training signals. In this paper, we introduce an agent that also maximises many other pseudo-reward functions simultaneously by reinforcement learning. All of these tasks share a common representation that, like unsupe...

Multilingual Lexicalized Constituency Parsing with Word-Level Auxiliary Tasks

We introduce a constituency parser based on a bi-LSTM encoder adapted from recent work (Cross and Huang, 2016b; Kiperwasser and Goldberg, 2016), which can incorporate a lower level character biLSTM (Ballesteros et al., 2015; Plank et al., 2016). We model two important interfaces of constituency parsing with auxiliary tasks supervised at the word level: (i) part-of-speech (POS) and morphological...

Multitask Learning with Low-Level Auxiliary Tasks for Encoder-Decoder Based Speech Recognition

End-to-end training of deep learning-based models allows for implicit learning of intermediate representations based on the final task loss. However, the end-to-end approach ignores the useful domain knowledge encoded in explicit intermediate-level supervision. We hypothesize that using intermediate representations as auxiliary supervision at lower levels of deep networks may be a good way of c...

Auxiliary placement in Rangi: A case of contact-induced change?

Presenting a New Method Based on Branch Placement for Optimal Placement of Phasor Measurement Units

In this paper, a new method based on branch placement for the optimal positioning of Phasor Measurement Units (PMUs) in power systems is proposed. In this method, the PMUs are in type of single-channel and are installed at the beginning of the branches. Therefore, they are able to measure the bus voltages. Also, the installation of the PMUs on the branches increases the security of observabilit...