My name is Filip Projcheski, I am 23 years old and I am a Computer Science Engineer and a Machine Learning/Data Science enthusiast. I have skills in a couple of programming languages including Python, C#, Java, R, C/C and JavaScript. I work as a Software Engineer in a new startup where we work on very interesting projects like: making costumes for VR games, making Instagram bots that will make you an influencer, as well as many CRUD web applications. My favorite AI fields are: Reinforcement Learning, Computer Vision and Time-Series Analyses.

Future AI applications require performance, reliability and privacy that the existing, cloud-dependant system architectures cannot provide. In this article, we study orchestration in the device-edge-cloud continuum, and focus on edge AI for resource orchestration. We claim that to support the constantly growing requirements of intelligent applications in the device-edge-cloud computing continuum, resource orchestration needs to embrace edge AI and emphasize local autonomy and intelligence. To justify the claim, we provide a general definition for continuum orchestration, and look at how current and emerging orchestration paradigms are suitable for the computing continuum. We describe certain major emerging research themes that may affect future orchestration, and provide an early vision of an orchestration paradigm that embraces those research themes. Finally, we survey current key edge AI methods and look at how they may contribute into fulfilling the vision of future continuum orchestration.

We investigate the applicability of deep reinforcement learning algorithms to the adaptive initial access beam alignment problem for mmWave communications using the state-of-the-art proximal policy optimization algorithm as an example. In comparison to recent unsupervised learning based approaches developed to tackle this problem, deep reinforcement learning has the potential to address a new and wider range of applications, since, in principle, no (differentiable) model of the channel and/or the whole system is required for training, and only agent-environment interactions are necessary to learn an algorithm (be it online or using a recorded dataset). We show that, although the chosen off-the-shelf deep reinforcement learning agent fails to perform well when trained on realistic problem sizes, introducing action space shaping in the form of beamforming modules vastly improves the performance, without sacrificing much generalizability. Using this add-on, the agent is able to deliver competitive performance to various state-of-the-art methods on simulated environments, even under realistic problem sizes. This demonstrates that through well-directed modification, deep reinforcement learning may have a chance to compete with other approaches in this area, opening up many straightforward extensions to other/similar scenarios.

Preference-based Reinforcement Learning (PbRL) methods utilize binary feedback from the human in the loop (HiL) over queried trajectory pairs to learn a reward model in an attempt to approximate the human's underlying reward function capturing their preferences. In this work, we investigate the issue of a high degree of variability in the initialized reward models which are sensitive to random seeds of the experiment. This further compounds the issue of degenerate reward functions PbRL methods already suffer from. We propose a data-driven reward initialization method that does not add any additional cost to the human in the loop and negligible cost to the PbRL agent and show that doing so ensures that the predicted rewards of the initialized reward model are uniform in the state space and this reduces the variability in the performance of the method across multiple runs and is shown to improve the overall performance compared to other initialization methods.

Reinforcement Learning has suffered from poor reward specification, and issues for reward hacking even in simple enough domains. Preference Based Reinforcement Learning attempts to solve the issue by utilizing binary feedbacks on queried trajectory pairs by a human in the loop indicating their preferences about the agent's behavior to learn a reward model. In this work, we present a state augmentation technique that allows the agent's reward model to be robust and follow an invariance consistency that significantly improved performance, i.e. the reward recovery and subsequent return computed using the learned policy over our baseline PEBBLE. We validate our method on three domains, Mountain Car, a locomotion task of Quadruped-Walk, and a robotic manipulation task of Sweep-Into, and find that using the proposed augmentation the agent not only benefits in the overall performance but does so, quite early in the agent's training phase.

We investigate the potential of Multi-Objective, Deep Reinforcement Learning for stock and cryptocurrency single-asset trading: in particular, we consider a Multi-Objective algorithm which generalizes the reward functions and discount factor (i.e., these components are not specified a priori, but incorporated in the learning process). Firstly, using several important assets (cryptocurrency pairs BTCUSD, ETHUSDT, XRPUSDT, and stock indexes AAPL, SPY, NIFTY50), we verify the reward generalization property of the proposed Multi-Objective algorithm, and provide preliminary statistical evidence showing increased predictive stability over the corresponding Single-Objective strategy. Secondly, we show that the Multi-Objective algorithm has a clear edge over the corresponding Single-Objective strategy when the reward mechanism is sparse (i.e., when non-null feedback is infrequent over time). Finally, we discuss the generalization properties with respect to the discount factor. The entirety of our code is provided in open source format.

Reinforcement learning (RL) has been extensively researched for enhancing human-environment interactions in various human-centric tasks, including e-learning and healthcare. Since deploying and evaluating policies online are high-stakes in such tasks, off-policy evaluation (OPE) is crucial for inducing effective policies. In human-centric environments, however, OPE is challenging because the underlying state is often unobservable, while only aggregate rewards can be observed (students' test scores or whether a patient is released from the hospital eventually). In this work, we propose a human-centric OPE (HOPE) to handle partial observability and aggregated rewards in such environments. Specifically, we reconstruct immediate rewards from the aggregated rewards considering partial observability to estimate expected total returns. We provide a theoretical bound for the proposed method, and we have conducted extensive experiments in real-world human-centric tasks, including sepsis treatments and an intelligent tutoring system. Our approach reliably predicts the returns of different policies and outperforms state-of-the-art benchmarks using both standard validation methods and human-centric significance tests.

Thompson sampling (TS) is a popular heuristic for action selection, but it requires sampling from a posterior distribution. Unfortunately, this can become computationally intractable in complex environments, such as those modeled using neural networks. Approximate posterior samples can produce effective actions, but only if they reasonably approximate joint predictive distributions of outputs across inputs. Notably, accuracy of marginal predictive distributions does not suffice. Epistemic neural networks (ENNs) are designed to produce accurate joint predictive distributions. We compare a range of ENNs through computational experiments that assess their performance in approximating TS across bandit and reinforcement learning environments. The results indicate that ENNs serve this purpose well and illustrate how the quality of joint predictive distributions drives performance. Further, we demonstrate that the \textit{epinet} -- a small additive network that estimates uncertainty -- matches the performance of large ensembles at orders of magnitude lower computational cost. This enables effective application of TS with computation that scales gracefully to complex environments.

However, much of the successes reinforces the fact that much of the explored trajectories have also been attributed to well specified reward functions do not actually participate in the reward learning process which ground the agent's behavior and subsequent task in and in fact their best change to affect the reward function the expected manner. As prior works have argued, the specification is once they get sampled and queried to the human in the of low level reward functions for seemingly easy loop. We posit that this untapped data source can greatly tasks could be quite difficult and may still result in inexplicable improve reward recovery and reduce the feedback sample and unexpected results (Verma et al. 2019, 2021; complexity. Our second observation notes that the reward Gopalakrishnan, Verma, and Kambhampati 2021a,b) potentially function being learnt may not conform to the structure of affecting trust between Human-AI (Zahedi et al. 2021, the state space simply because it doesn't get exposed to as 2022). For example, works like (Krakovna et al. 2020; Vamplew many data points (in comparison to, say, the policy approximation et al. 2018) have raised the issues of reward hacking function). We utilize our observations to improve and reward exploitation where the RL agents would discover performance of RL agents in recovering the underlying behaviors that seems to be "cheating" or incorrect and reward function and learn a good policy by exploiting the yet maximize the expected cumulative reward. This has also rich unlabeled trajectory data. Although works like SURF gotten attention from the explainable AI community where (Park et al. 2022) have proposed a semi-supervised learning they attempt to analyze whether the agent is actually behaving approach to utilize unlabeled trajectory data, they would in the intended manner (Verma, Kharkwal, and Kambhampati generate labels for unlabeled trajectories and use these 2022; Sreedharan et al. 2020; Kambhampati et al. data points as if they were given by the human in the loop.

Offline goal-conditioned reinforcement learning (GCRL) can be challenging due to overfitting to the given dataset. To generalize agents' skills outside the given dataset, we propose a goal-swapping procedure that generates additional trajectories. To alleviate the problem of noise and extrapolation errors, we present a general offline reinforcement learning method called deterministic Q-advantage policy gradient (DQAPG). In the experiments, DQAPG outperforms state-of-the-art goal-conditioned offline RL methods in a wide range of benchmark tasks, and goal-swapping further improves the test results. It is noteworthy, that the proposed method obtains good performance on the challenging dexterous in-hand manipulation tasks for which the prior methods failed.