**Blue River Controls** is a tool that allows users to train and test reinforcement learning algorithms on real-world hardware. It features a simple interface based on OpenAI Gym, that works directly on both simulation and hardware.

**SRU**, or **Simple Recurrent Unit**, is a recurrent neural unit with a light form of recurrence. SRU exhibits the same level of parallelism as [convolution](https://paperswithcode.com/method/convolution) and [feed-forward nets](https://paperswithcode.com/methods/category/feedforward-networks). This is achieved by balancing sequential dependence and independence: while the state computation of SRU is time-dependent, each state dimension is independent. This simplification enables CUDA-level optimizations that parallelize the computation across hidden dimensions and time steps, effectively using the full capacity of modern GPUs. 

SRU also replaces the use of convolutions (i.e., ngram filters), as in [QRNN](https://paperswithcode.com/method/qrnn) and KNN, with more recurrent connections. This retains modeling capacity, while using less computation (and hyper-parameters). Additionally, SRU improves the training of deep recurrent models by employing [highway connections](https://paperswithcode.com/method/highway-layer) and a parameter initialization scheme tailored for gradient propagation in deep architectures.

A single layer of SRU involves the following computation:

$$
\mathbf{f}\_{t} =\sigma\left(\mathbf{W}\_{f} \mathbf{x}\_{t}+\mathbf{v}\_{f} \odot \mathbf{c}\_{t-1}+\mathbf{b}\_{f}\right) 
$$

$$
\mathbf{c}\_{t} =\mathbf{f}\_{t} \odot \mathbf{c}\_{t-1}+\left(1-\mathbf{f}\_{t}\right) \odot\left(\mathbf{W} \mathbf{x}\_{t}\right) \\
$$

$$
\mathbf{r}\_{t} =\sigma\left(\mathbf{W}\_{r} \mathbf{x}\_{t}+\mathbf{v}\_{r} \odot \mathbf{c}\_{t-1}+\mathbf{b}\_{r}\right) \\
$$

$$
\mathbf{h}\_{t} =\mathbf{r}\_{t} \odot \mathbf{c}\_{t}+\left(1-\mathbf{r}\_{t}\right) \odot \mathbf{x}\_{t}
$$

where $\mathbf{W}, \mathbf{W}\_{f}$ and $\mathbf{W}\_{r}$ are parameter matrices and $\mathbf{v}\_{f}, \mathbf{v}\_{r}, \mathbf{b}\_{f}$ and $\mathbf{b}_{v}$ are parameter vectors to be learnt during training. The complete architecture decomposes to two sub-components: a light recurrence and a highway network,

The light recurrence component successively reads the input vectors $\mathbf{x}\_{t}$ and computes the sequence of states $\mathbf{c}\_{t}$ capturing sequential information. The computation resembles other recurrent networks such as [LSTM](https://paperswithcode.com/method/lstm), [GRU](https://paperswithcode.com/method/gru) and RAN. Specifically, a forget gate $\mathbf{f}\_{t}$ controls the information flow and the state vector $\mathbf{c}\_{t}$ is determined by adaptively averaging the previous state $\mathbf{c}\_{t-1}$ and the current observation $\mathbf{W} \mathbf{x}_{+}$according to $\mathbf{f}\_{t}$.

Simple Recurrent Units for Highly Parallelizable Recurrence

Blue River Controls

Blue River Controls: A toolkit for Reinforcement Learning Control Systems on Hardware

**TILDEv2** is a [BERT](https://paperswithcode.com/method/bert)-based re-ranking method that stems from [TILDE](https://dl.acm.org/doi/abs/10.1145/3404835.3462922) but that addresses its limitations. It relies on contextualized exact term matching with expanded passages. This requires to only store in the index the score of tokens that appear in the expanded passages (rather than all the vocabulary), thus producing indexes that are 99% smaller than those of the original.

Specifically, TILDE is modified in the following aspects:

- **Exact Term Matching**. The query likelihood matching originally employed in TILDE, expands passages into the BERT vocabulary size, resulting in large indexes. To overcome this issue, estimating relevance scores is achieved with contextualized exact term matching. This allows the model to index tokens only present in the passage, thus reducing the index size. In addition to this, we replace the query likelihood loss function, with the Noise contrastive estimation (NCE) loss that allows to better leverage negative training samples. 
 
- **Passage Expansion**. To overcome the vocabulary mismatch problem that affects exact term matching methods, passage expansion is used to expand the original passage collection. Passages in the collection are expanded using deep LMs with a limited number of tokens. This requires TILDEv2 to only index a few extra tokens in addition to those in the original passages.

Source	Blue River Controls: A toolkit for Reinforcement Learning Control Systems on Hardware
Year	2000
Data Source	CC BY-SA - https://paperswithcode.com