A Review of Uncertainty for Deep Reinforcement Learning

Uncertainty is ubiquitous in games, both in the agents playing games and often in the games themselves. Working with uncertainty is therefore an important component of successful deep reinforcement learning agents. While there has been substantial effort and progress in understanding and working with uncertainty for supervised learning, the body of literature for uncertainty aware deep reinforcement learning is less developed. While many of the same problems regarding uncertainty in neural networks for supervised learning remain for reinforcement learning, there are additional sources of uncertainty due to the nature of an interactable environment. In this work, we provide an overview motivating and presenting existing techniques in uncertainty aware deep reinforcement learning. These works show empirical benefits on a variety of reinforcement learning tasks. This work serves to help to centralize the disparate results and promote future research in this area.

An Empirical Review of Optimization Techniques for Quantum Variational Circuits

Quantum Variational Circuits (QVCs) are often claimed as one of the most potent uses of both near term and long term quantum hardware. The standard approaches to optimizing these circuits rely on a classical system to compute the new parameters at every optimization step. However, this process can be extremely challenging, due to the nature of navigating the exponentially scaling complex Hilbert space, barren plateaus, and the noise present in all foreseeable quantum hardware. Although a variety of optimization algorithms are employed in practice, there is often a lack of theoretical or empirical motivations for this choice. To this end we empirically evaluate the potential of many common gradient and gradient free optimizers on a variety of optimization tasks. These tasks include both classical and quantum data based optimization routines. Our evaluations were conducted in both noise free and noisy simulations. The large number of problems and optimizers evaluated yields strong empirical guidance for choosing optimizers for QVCs that is currently lacking.

Optimizing Quantum Variational Circuits with Deep Reinforcement Learning

Quantum Machine Learning (QML) is considered to be one of the most promising applications of near term quantum devices. However, the optimization of quantum machine learning models presents numerous challenges arising from the imperfections of hardware and the fundamental obstacles in navigating an exponentially scaling Hilbert space. In this work, we evaluate the potential of contemporary methods in deep reinforcement learning to augment gradient based optimization routines in quantum variational circuits. We find that reinforcement learning augmented optimizers consistently outperform gradient descent in noisy environments. All code and pretrained weights are available to replicate the results or deploy the models at https://github.com/lockwo/rl_qvc_opt.

In Defense of the Paper

The machine learning publication process is broken, of that there can be no doubt. Many of these flaws are attributed to the current workflow: LaTeX to PDF to reviewers to camera ready PDF. This has understandably resulted in the desire for new forms of publications; ones that can increase inclusively, accessibility and pedagogical strength. However, this venture fails to address the origins of these inadequacies in the contemporary paper workflow. The paper, being the basic unit of academic research, is merely how problems in the publication and research ecosystem manifest; but is not itself responsible for them. Not only will simply replacing or augmenting papers with different formats not fix existing problems; when used as a band-aid without systemic changes, will likely exacerbate the existing inequities. In this work, we argue that the root cause of hindrances in the accessibility of machine learning research lies not in the paper workflow but within the misaligned incentives behind the publishing and research processes. We discuss these problems and argue that the paper is the optimal workflow. We also highlight some potential solutions for the incentivization problems.

Reinforcement Learning with Quantum Variational Circuits

The development of quantum computational techniques has advanced greatly in recent years, parallel to the advancements in techniques for deep reinforcement learning. This work explores the potential for quantum computing to facilitate reinforcement learning problems. Quantum computing approaches offer important potential improvements in time and space complexity over traditional algorithms because of its ability to exploit the quantum phenomena of superposition and entanglement. Specifically, we investigate the use of quantum variational circuits, a form of quantum machine learning. We present our techniques for encoding classical data for a quantum variational circuit, we further explore pure and hybrid quantum algorithms for DQN and Double DQN. Our results indicate both hybrid and pure quantum variational circuit have the ability to solve reinforcement learning tasks with a smaller parameter space. These comparison are conducted with two OpenAI Gym environments: CartPole and Blackjack, The success of this work is indicative of a strong future relationship between quantum machine learning and deep reinforcement learning.