Sample Efficient Reinforcement Learning from Human Feedback via Active Exploration

Preference-based feedback is important for many applications in reinforcement learning where direct evaluation of a reward function is not feasible. A notable recent example arises in reinforcement learning from human feedback (RLHF) on large language models. For many applications of RLHF, the cost of acquiring the human feedback can be substantial. In this work, we take advantage of the fact that one can often choose contexts at which to obtain human feedback in order to most efficiently identify a good policy, and formalize this as an offline contextual dueling bandit problem. We give an upper-confidence-bound style algorithm for this problem and prove a polynomial worst-case regret bound. We then provide empirical confirmation in a synthetic setting that our approach outperforms existing methods. After, we extend the setting and methodology for practical use in RLHF training of large language models. Here, our method is able to reach better performance with fewer samples of human preferences than multiple baselines on three real-world datasets.

Kernelized Offline Contextual Dueling Bandits

Preference-based feedback is important for many applications where direct evaluation of a reward function is not feasible. A notable recent example arises in reinforcement learning from human feedback on large language models. For many of these applications, the cost of acquiring the human feedback can be substantial or even prohibitive. In this work, we take advantage of the fact that often the agent can choose contexts at which to obtain human feedback in order to most efficiently identify a good policy, and introduce the offline contextual dueling bandit setting. We give an upper-confidence-bound style algorithm for this setting and prove a regret bound. We also give empirical confirmation that this method outperforms a similar strategy that uses uniformly sampled contexts.

Best Arm Identification under Additive Transfer Bandits

We consider a variant of the best arm identification (BAI) problem in multi-armed bandits (MAB) in which there are two sets of arms (source and target), and the objective is to determine the best target arm while only pulling source arms. In this paper, we study the setting when, despite the means being unknown, there is a known additive relationship between the source and target MAB instances. We show how our framework covers a range of previously studied pure exploration problems and additionally captures new problems. We propose and theoretically analyze an LUCB-style algorithm to identify an $\epsilon$-optimal target arm with high probability. Our theoretical analysis highlights aspects of this transfer learning problem that do not arise in the typical BAI setup, and yet recover the LUCB algorithm for single domain BAI as a special case.

A Design Methodology for Efficient Implementation of Deconvolutional Neural Networks on an FPGA

In recent years deep learning algorithms have shown extremely high performance on machine learning tasks such as image classification and speech recognition. In support of such applications, various FPGA accelerator architectures have been proposed for convolutional neural networks (CNNs) that enable high performance for classification tasks at lower power than CPU and GPU processors. However, to date, there has been little research on the use of FPGA implementations of deconvolutional neural networks (DCNNs). DCNNs, also known as generative CNNs, encode high-dimensional probability distributions and have been widely used for computer vision applications such as scene completion, scene segmentation, image creation, image denoising, and super-resolution imaging. We propose an FPGA architecture for deconvolutional networks built around an accelerator which effectively handles the complex memory access patterns needed to perform strided deconvolutions, and that supports convolution as well. We also develop a three-step design optimization method that systematically exploits statistical analysis, design space exploration and VLSI optimization. To verify our FPGA deconvolutional accelerator design methodology we train DCNNs offline on two representative datasets using the generative adversarial network method (GAN) run on Tensorflow, and then map these DCNNs to an FPGA DCNN-plus-accelerator implementation to perform generative inference on a Xilinx Zynq-7000 FPGA. Our DCNN implementation achieves a peak performance density of 0.012 GOPs/DSP.

A Nonparametric Framework for Quantifying Generative Inference on Neuromorphic Systems

Restricted Boltzmann Machines and Deep Belief Networks have been successfully used in probabilistic generative model applications such as image occlusion removal, pattern completion and motion synthesis. Generative inference in such algorithms can be performed very efficiently on hardware using a Markov Chain Monte Carlo procedure called Gibbs sampling, where stochastic samples are drawn from noisy integrate and fire neurons implemented on neuromorphic substrates. Currently, no satisfactory metrics exist for evaluating the generative performance of such algorithms implemented on high-dimensional data for neuromorphic platforms. This paper demonstrates the application of nonparametric goodness-of-fit testing to both quantify the generative performance as well as provide decision-directed criteria for choosing the parameters of the neuromorphic Gibbs sampler and optimizing usage of hardware resources used during sampling.