Reinforcement learning is finding its way to real-world problem application, transferring from simulated environments to physical setups. In this work, we implement vision-based alignment of an optical Mach-Zehnder interferometer with a confocal telescope in one arm, which controls the diameter and divergence of the corresponding beam. We use a continuous action space; exponential scaling enables us to handle actions within a range of over two orders of magnitude. Our agent trains only in a simulated environment with domain randomizations. In an experimental evaluation, the agent significantly outperforms an existing solution and a human expert.

In this paper, we study the problem of evaluating the addition of elements to a set. This problem is difficult, because it can, in the general case, not be reduced to unconditional preferences between the choices. Therefore, we model preferences based on the context of the decision. We discuss and compare two different Siamese network architectures for this task: a twin network that compares the two sets resulting after the addition, and a triplet network that models the contribution of each candidate to the existing set. We evaluate the two settings on a real-world task; learning human card preferences for deck building in the collectible card game Magic: The Gathering. We show that the triplet approach achieves a better result than the twin network and that both outperform previous results on this task.

In my previous post A First Look at Reinforcement Learning, I attempted to use Deep Q learning to solve the CartPole problem. In this post, I will be further exploring Deep Q learning but in the…

Learning algorithms tend to struggle [4]. Hierarchical Reinforcement Learning, or HRL, takes advantage of the hierarchical Pipelines networks are the fulcrum of the oil and gas policy decomposition to exploit underlying problem industries and of gas and water mains. These pipes must structures and simplify the learning of complex tasks. The hierarchical be periodically inspected to guarantee the safety and proper decomposition can be either defined by using prior functioning of the plants. However, inspection is usually knowledge [5], [6], [7], [8], or can be automatically learned a long, expensive and tedious procedure that requires the during training [4], [9], [10]. While the latter category of shut-down of the whole plant and, in the specific case of algorithm does not require expert knowledge for defining industrial pipelines, the removal of the insulation around the the hierarchy, the autonomous discovery of the options often pipes. With metal pipes, the inspection is currently performed leads to sub-optimal policies if additional regularizers are not from the outside using ultrasonic or magnetic probes that used during the learning phase [7], [10].

Learning in multi-agent systems is highly challenging due to the inherent complexity introduced by agents' interactions. We tackle systems with a huge population of interacting agents (e.g., swarms) via Mean-Field Control (MFC). MFC considers an asymptotically infinite population of identical agents that aim to collaboratively maximize the collective reward. Specifically, we consider the case of unknown system dynamics where the goal is to simultaneously optimize for the rewards and learn from experience. We propose an efficient model-based reinforcement learning algorithm $\text{M}^3\text{-UCRL}$ that runs in episodes and provably solves this problem. $\text{M}^3\text{-UCRL}$ uses upper-confidence bounds to balance exploration and exploitation during policy learning. Our main theoretical contributions are the first general regret bounds for model-based RL for MFC, obtained via a novel mean-field type analysis. $\text{M}^3\text{-UCRL}$ can be instantiated with different models such as neural networks or Gaussian Processes, and effectively combined with neural network policy learning. We empirically demonstrate the convergence of $\text{M}^3\text{-UCRL}$ on the swarm motion problem of controlling an infinite population of agents seeking to maximize location-dependent reward and avoid congested areas.

Text Worlds are virtual environments for embodied agents that, unlike 2D or 3D environments, are rendered exclusively using textual descriptions. These environments offer an alternative to higher-fidelity 3D environments due to their low barrier to entry, providing the ability to study semantics, compositional inference, and other high-level tasks with rich high-level action spaces while controlling for perceptual input. This systematic survey outlines recent developments in tooling, environments, and agent modeling for Text Worlds, while examining recent trends in knowledge graphs, common sense reasoning, transfer learning of Text World performance to higher-fidelity environments, as well as near-term development targets that, once achieved, make Text Worlds an attractive general research paradigm for natural language processing.

Many hierarchical reinforcement learning (RL) applications have empirically verified that incorporating prior knowledge in reward design improves convergence speed and practical performance. We attempt to quantify the computational benefits of hierarchical RL from a planning perspective under assumptions about the intermediate state and intermediate rewards frequently (but often implicitly) adopted in practice. Our approach reveals a trade-off between computational complexity and the pursuit of the shortest path in hierarchical planning: using intermediate rewards significantly reduces the computational complexity in finding a successful policy but does not guarantee to find the shortest path, whereas using sparse terminal rewards finds the shortest path at a significantly higher computational cost. We also corroborate our theoretical results with extensive experiments on the MiniGrid environments using Q-learning and other popular deep RL algorithms.

Imitation learning enables agents to reuse and adapt the hard-won expertise of others, offering a solution to several key challenges in learning behavior. Although it is easy to observe behavior in the real-world, the underlying actions may not be accessible. We present a new method for imitation solely from observations that achieves comparable performance to experts on challenging continuous control tasks while also exhibiting robustness in the presence of observations unrelated to the task. Our method, which we call FORM (for "Future Observation Reward Model") is derived from an inverse RL objective and imitates using a model of expert behavior learned by generative modelling of the expert's observations, without needing ground truth actions. We show that FORM performs comparably to a strong baseline IRL method (GAIL) on the DeepMind Control Suite benchmark, while outperforming GAIL in the presence of task-irrelevant features.

Influence maximization is the problem of finding a small subset of nodes in a network that can maximize the diffusion of information. Recently, it has also found application in HIV prevention, substance abuse prevention, micro-finance adoption, etc., where the goal is to identify the set of peer leaders in a real-world physical social network who can disseminate information to a large group of people. Unlike online social networks, real-world networks are not completely known, and collecting information about the network is costly as it involves surveying multiple people. In this paper, we focus on this problem of network discovery for influence maximization. The existing work in this direction proposes a reinforcement learning framework. As the environment interactions in real-world settings are costly, so it is important for the reinforcement learning algorithms to have minimum possible environment interactions, i.e, to be sample efficient. In this work, we propose CLAIM - Curriculum LeArning Policy for Influence Maximization to improve the sample efficiency of RL methods. We conduct experiments on real-world datasets and show that our approach can outperform the current best approach.

This paper investigates the problem of providing ultra-reliable and energy-efficient virtual reality (VR) experiences for wireless mobile users. To ensure reliable ultra-high-definition (UHD) video frame delivery to mobile users and enhance their immersive visual experiences, a coordinated multipoint (CoMP) transmission technique and millimeter wave (mmWave) communications are exploited. Owing to user movement and time-varying wireless channels, the wireless VR experience enhancement problem is formulated as a sequence-dependent and mixed-integer problem with a goal of maximizing users' feeling of presence (FoP) in the virtual world, subject to power consumption constraints on access points (APs) and users' head-mounted displays (HMDs). The problem, however, is hard to be directly solved due to the lack of users' accurate tracking information and the sequence-dependent and mixed-integer characteristics. To overcome this challenge, we develop a parallel echo state network (ESN) learning method to predict users' tracking information by training fresh and historical tracking samples separately collected by APs. With the learnt results, we propose a deep reinforcement learning (DRL) based optimization algorithm to solve the formulated problem. In this algorithm, we implement deep neural networks (DNNs) as a scalable solution to produce integer decision variables and solving a continuous power control problem to criticize the integer decision variables. Finally, the performance of the proposed algorithm is compared with various benchmark algorithms, and the impact of different design parameters is also discussed. Simulation results demonstrate that the proposed algorithm is more 4.14% energy-efficient than the benchmark algorithms.