Many methods for Model-based Reinforcement learning (MBRL) in Markov decision processes (MDPs) provide guarantees for both the accuracy of the model they can deliver and the learning efficiency. At the same time, state abstraction techniques allow for a reduction of the size of an MDP while maintaining a bounded loss with respect to the original problem. Therefore, it may come as a surprise that no such guarantees are available when combining both techniques, i.e., where MBRL merely observes abstract states. Our theoretical analysis shows that abstraction can introduce a dependence between samples collected online (e.g., in the real world). That means that, without taking this dependence into account, results for MBRL do not directly extend to this setting. Our result shows that we can use concentration inequalities for martingales to overcome this problem. This result makes it possible to extend the guarantees of existing MBRL algorithms to the setting with abstraction. We illustrate this by combining R-MAX, a prototypical MBRL algorithm, with abstraction, thus producing the first performance guarantees for model-based 'RL from Abstracted Observations': model-based reinforcement learning with an abstract model.

Standard deep reinforcement learning (DRL) aims to maximize expected reward, considering collected experiences equally in formulating a policy. This differs from human decision-making, where gains and losses are valued differently and outlying outcomes are given increased consideration. It also fails to capitalize on opportunities to improve safety and/or performance through the incorporation of distributional context. Several approaches to distributional DRL have been investigated, with one popular strategy being to evaluate the projected distribution of returns for possible actions. We propose a more direct approach whereby risk-sensitive objectives, specified in terms of the cumulative distribution function (CDF) of the distribution of full-episode rewards, are optimized. This approach allows for outcomes to be weighed based on relative quality, can be used for both continuous and discrete action spaces, and may naturally be applied in both constrained and unconstrained settings. We show how to compute an asymptotically consistent estimate of the policy gradient for a broad class of risk-sensitive objectives via sampling, subsequently incorporating variance reduction and regularization measures to facilitate effective on-policy learning. We then demonstrate that the use of moderately "pessimistic" risk profiles, which emphasize scenarios where the agent performs poorly, leads to enhanced exploration and a continual focus on addressing deficiencies. We test the approach using different risk profiles in six OpenAI Safety Gym environments, comparing to state of the art on-policy methods. Without cost constraints, we find that pessimistic risk profiles can be used to reduce cost while improving total reward accumulation. With cost constraints, they are seen to provide higher positive rewards than risk-neutral approaches at the prescribed allowable cost.

With more than 32% of the global energy used by commercial and residential buildings, there is an urgent need to revisit traditional approaches to Building Energy Management (BEM). With HVAC systems accounting for about 40% of the total energy cost in the commercial sector, we propose a low-complexity DRL-based model with multi-input multi-output architecture for the HVAC energy optimization of open-plan offices, which uses only a handful of controllable and accessible factors. The efficacy of our solution is evaluated through extensive analysis of the overall energy consumption and thermal comfort levels compared to a baseline system based on the existing HVAC schedule in a real building. This comparison shows that our method achieves 37% savings in energy consumption with minimum violation (<1%) of the desired temperature range during work hours. It takes only a total of 40 minutes for 5 epochs (about 7.75 minutes per epoch) to train a network with superior performance and covering diverse conditions for its low-complexity architecture; therefore, it easily adapts to changes in the building setups, weather conditions, occupancy rate, etc. Moreover, by enforcing smoothness on the control strategy, we suppress the frequent and unpleasant on/off transitions on HVAC units to avoid occupant discomfort and potential damage to the system. The generalizability of our model is verified by applying it to different building models and under various weather conditions.

Deep Reinforcement Learning (DRL) is a quickly evolving research field rooted in operations research and behavioural psychology, with potential applications extending across various domains, including robotics. This thesis delineates the background of modern Reinforcement Learning (RL), starting with the framework constituted by the Markov decision processes, Markov properties, goals and rewards, agent-environment interactions, and policies. We explain the main types of algorithms commonly used in RL, including value-based, policy gradient, and actor-critic methods, with a special emphasis on DQN, A2C and PPO. We then give a short literature review on some widely adopted frameworks for implementing RL algorithms and environments. Subsequently, we present Bidimensional Gripper Environment (BGE), a virtual simulator based on the Pymunk physics engine we developed to analyse top-down bidimensional object manipulation. The methodology section frames our agent-environment interaction as a Markov decision process, such that we can apply our RL algorithms. We list various goal formulation strategies, including reward shaping and curriculum learning. We also employ different steps of observation preprocessing to reduce the computational workload required. In the experimental phase, we run through a series of scenarios of increasing difficulty. We start with a simple static scenario and then gradually increase the amount of stochasticity. Whenever the agents show difficulty in learning, we counteract by increasing the degree of reward shaping and curriculum learning. These experiments demonstrate the substantial limitations and pitfalls of model-free algorithms under changing dynamics. In conclusion, we present a summary of our findings and remarks. We then outline potential future work to improve our methodology and possibly expand to real-world systems.

In this paper, we study the problem of joint active and passive beamforming for reconfigurable intelligent surface (RIS)-assisted massive multiple-input multiple-output systems towards the extension of the wireless cellular coverage in 3D, where multiple RISs, each equipped with an array of passive elements, are deployed to assist a base station (BS) to simultaneously serve multiple unmanned aerial vehicles (UAVs) in the same time-frequency resource of 5G wireless communications. With a focus on ensuring fairness among UAVs, our objective is to maximize the minimum signal-to-interference-plus-noise ratio (SINR) at UAVs by jointly optimizing the transmit beamforming parameters at the BS and phase shift parameters at RISs. We propose two novel algorithms to address this problem. The first algorithm aims to mitigate interference by calculating the BS beamforming matrix through matrix inverse operations once the phase shift parameters are determined. The second one is based on the principle that one RIS element only serves one UAV and the phase shift parameter of this RIS element is optimally designed to compensate the phase offset caused by the propagation and fading. To obtain the optimal parameters, we utilize one state-of-the-art reinforcement learning algorithm, deep deterministic policy gradient, to solve these two optimization problems. Simulation results are provided to illustrate the effectiveness of our proposed solution and some insightful remarks are observed.

Online games are dynamic environments where players interact with each other, which offers a rich setting for understanding how players negotiate their way through the game to an ultimate victory. This work studies online player interactions during the turn-based strategy game, Diplomacy. We annotated a dataset of over 10,000 chat messages for different negotiation strategies and empirically examined their importance in predicting long- and short-term game outcomes. Although negotiation strategies can be predicted reasonably accurately through the linguistic modeling of the chat messages, more is needed for predicting short-term outcomes such as trustworthiness. On the other hand, they are essential in graph-aware reinforcement learning approaches to predict long-term outcomes, such as a player's success, based on their prior negotiation history. We close with a discussion of the implications and impact of our work. The dataset is available at https://github.com/kj2013/claff-diplomacy.

Inverse Reinforcement Learning (IRL) learns an optimal policy, given some expert demonstrations, thus avoiding the need for the tedious process of specifying a suitable reward function. However, current methods are constrained by at least one of the following requirements. The first one is the need to fully solve a forward Reinforcement Learning (RL) problem in the inner loop of the algorithm, which might be prohibitively expensive in many complex environments. The second one is the need for full trajectories from the experts, which might not be easily available. The third one is the assumption that the expert data is homogeneous rather than a collection from various experts or possibly alternative solutions to the same task. Such constraints make IRL approaches either not scalable or not usable on certain existing systems. In this work we propose an approach which removes these requirements through a dynamic, adaptive method called Adversarial Imitation Learning on Aggregated Data (AILAD). It learns conjointly both a non linear reward function and the associated optimal policy using an adversarial framework. The reward learner only uses aggregated data. Moreover, it generates diverse behaviors producing a distribution over the aggregated data matching that of the experts.

Domain Generalization (DG) techniques have emerged as a popular approach to address the challenges of domain shift in Deep Learning (DL), with the goal of generalizing well to the target domain unseen during the training. In recent years, numerous methods have been proposed to address the DG setting, among which one popular approach is the adversarial learning-based methodology. The main idea behind adversarial DG methods is to learn domain-invariant features by minimizing a discrepancy metric. However, most adversarial DG methods use 0-1 loss based $\mathcal{H}\Delta\mathcal{H}$ divergence metric. In contrast, the margin loss-based discrepancy metric has the following advantages: more informative, tighter, practical, and efficiently optimizable. To mitigate this gap, this work proposes a novel adversarial learning DG algorithm, MADG, motivated by a margin loss-based discrepancy metric. The proposed MADG model learns domain-invariant features across all source domains and uses adversarial training to generalize well to the unseen target domain. We also provide a theoretical analysis of the proposed MADG model based on the unseen target error bound. Specifically, we construct the link between the source and unseen domains in the real-valued hypothesis space and derive the generalization bound using margin loss and Rademacher complexity. We extensively experiment with the MADG model on popular real-world DG datasets, VLCS, PACS, OfficeHome, DomainNet, and TerraIncognita. We evaluate the proposed algorithm on DomainBed's benchmark and observe consistent performance across all the datasets.

We focus on the task of approximating the optimal value function in deep reinforcement learning. This iterative process is comprised of solving a sequence of optimization problems where the loss function changes per iteration. The common approach to solving this sequence of problems is to employ modern variants of the stochastic gradient descent algorithm such as Adam. These optimizers maintain their own internal parameters such as estimates of the first-order and the second-order moments of the gradient, and update them over time. Therefore, information obtained in previous iterations is used to solve the optimization problem in the current iteration. We demonstrate that this can contaminate the moment estimates because the optimization landscape can change arbitrarily from one iteration to the next one. To hedge against this negative effect, a simple idea is to reset the internal parameters of the optimizer when starting a new iteration. We empirically investigate this resetting idea by employing various optimizers in conjunction with the Rainbow algorithm. We demonstrate that this simple modification significantly improves the performance of deep RL on the Atari benchmark.

We introduce AdCraft, a novel benchmark environment for the Reinforcement Learning (RL) community distinguished by its stochastic and non-stationary properties. The environment simulates bidding and budgeting dynamics within Search Engine Marketing (SEM), a digital marketing technique utilizing paid advertising to enhance the visibility of websites on search engine results pages (SERPs). The performance of SEM advertisement campaigns depends on several factors, including keyword selection, ad design, bid management, budget adjustments, and performance monitoring. Deep RL recently emerged as a potential strategy to optimize campaign profitability within the complex and dynamic landscape of SEM, but it requires substantial data, which may be costly or infeasible to acquire in practice. Our customizable environment enables practitioners to assess and enhance the robustness of RL algorithms pertinent to SEM bid and budget management without such costs. Through a series of experiments within the environment, we demonstrate the challenges imposed by sparsity and non-stationarity on agent convergence and performance. We hope these challenges further encourage discourse and development around effective strategies for managing real-world uncertainties.