Particle Physics Model Building with Reinforcement Learning

Machine-learning techniques are emerging as a valuable tool in experimental physics, and among them, reinforcement learning offers the potential to control high-dimensional, multistage processes in the presence of fluctuating environments. In this experimental work, we apply reinforcement learning to the preparation of an ultracold quantum gas to realize a consistent and large number of atoms at microkelvin temperatures. This reinforcement learning agent determines an optimal...

In this paper, we introduce a novel form of value function, $Q(s, s')$, that expresses the utility of transitioning from a state $s$ to a neighboring state $s'$ and then acting optimally thereafter. In order to derive an optimal policy, we develop a forward dynamics model that learns to make next-state predictions that maximize this value. This formulation decouples actions from values while still learning off-policy. We highlight the benefits of this approach in terms of val...

In this paper, we present a Bayesian view on model-based reinforcement learning. We use expert knowledge to impose structure on the transition model and present an efficient learning scheme based on variational inference. This scheme is applied to a heteroskedastic and bimodal benchmark problem on which we compare our results to NFQ and show how our approach yields human-interpretable insight about the underlying dynamics while also increasing data-efficiency.

Free energy-based reinforcement learning (FERL) with clamped quantum Boltzmann machines (QBM) was shown to significantly improve the learning efficiency compared to classical Q-learning with the restriction, however, to discrete state-action space environments. In this paper, the FERL approach is extended to multi-dimensional continuous state-action space environments to open the doors for a broader range of real-world applications. First, free energy-based Q-learning is stud...

This paper is concerned with the design of algorithms based on systems of interacting particles to represent, approximate, and learn the optimal control law for reinforcement learning (RL). The primary contribution of the present paper is to show that convergence rates can be accelerated dramatically through careful design of interactions between particles. Theory focuses on the linear quadratic stochastic optimal control problem for which a complete and novel theory is prese...

In these proceedings, we present a library allowing for straightforward calls in C++ to jet grooming algorithms trained with deep reinforcement learning. The RL agent is trained with a reward function constructed to optimize the groomed jet properties, using both signal and background samples in a simultaneous multi-level training. We show that the grooming algorithm derived from the deep RL agent can match state-of-the-art techniques used at the Large Hadron Collider, result...

Deep Reinforcement Learning has enabled the learning of policies for complex tasks in partially observable environments, without explicitly learning the underlying model of the tasks. While such model-free methods achieve considerable performance, they often ignore the structure of task. We present a natural representation of to Reinforcement Learning (RL) problems using Recurrent Convolutional Neural Networks (RCNNs), to better exploit this inherent structure. We define 3 su...

The goal of reinforcement learning (RL) is to let an agent learn an optimal control policy in an unknown environment so that future expected rewards are maximized. The model-free RL approach directly learns the policy based on data samples. Although using many samples tends to improve the accuracy of policy learning, collecting a large number of samples is often expensive in practice. On the other hand, the model-based RL approach first estimates the transition model of the e...

We propose deep reinforcement learning as a model-free method for exploring the landscape of string vacua. As a concrete application, we utilize an artificial intelligence agent known as an asynchronous advantage actor-critic to explore type IIA compactifications with intersecting D6-branes. As different string background configurations are explored by changing D6-brane configurations, the agent receives rewards and punishments related to string consistency conditions and pro...

Classical methods to control heating systems are often marred by suboptimal performance, inability to adapt to dynamic conditions and unreasonable assumptions e.g. existence of building models. This paper presents a novel deep reinforcement learning algorithm which can control space heating in buildings in a computationally efficient manner, and benchmarks it against other known techniques. The proposed algorithm outperforms rule based control by between 5-10% in a simulation...