The field of artificial intelligence (AI) is devoted to the creation of artificial decision-makers that can perform (at least) on par with the human counterparts on a domain of interest. Unlike the agents in traditional AI, the agents in artificial general intelligence (AGI) are required to replicate human intelligence in almost every domain of interest. Moreover, an AGI agent should be able to achieve this without (virtually any) further changes, retraining, or fine-tuning of the parameters. The real world is non-stationary, non-ergodic, and non-Markovian: we, humans, can neither revisit our past nor are the most recent observations sufficient statistics. Yet, we excel at a variety of complex tasks. Many of these tasks require longterm planning. We can associate this success to our natural faculty to abstract away task-irrelevant information from our overwhelming sensory experience. We make task-specific mental models of the world without much effort. Due to this ability to abstract, we can plan on a significantly compact representation of a task without much loss of performance. Not only this, we also abstract our actions to produce high-level plans: the level of action-abstraction can be anywhere between small muscle movements to a mental notion of "doing an action". It is natural to assume that any AGI agent competing with humans (at every plausible domain) should also have these abilities to abstract its experiences and actions. This thesis is an inquiry into the existence of such abstractions which aid efficient planing for a wide range of domains, and most importantly, these abstractions come with some optimality guarantees.

The field of General Reinforcement Learning (GRL) formulates the problem of sequential decision-making from ground up. The history of interaction constitutes a "ground" state of the system, which never repeats. On the one hand, this generality allows GRL to model almost every domain possible, e.g.\ Bandits, MDPs, POMDPs, PSRs, and history-based environments. On the other hand, in general, the near-optimal policies in GRL are functions of complete history, which hinders not only learning but also planning in GRL. The usual way around for the planning part is that the agent is given a Markovian abstraction of the underlying process. So, it can use any MDP planning algorithm to find a near-optimal policy. The Extreme State Aggregation (ESA) framework has extended this idea to non-Markovian abstractions without compromising on the possibility of planning through a (surrogate) MDP. A distinguishing feature of ESA is that it proves an upper bound of $O\left(\varepsilon^{-A} \cdot (1-\gamma)^{-2A}\right)$ on the number of states required for the surrogate MDP (where $A$ is the number of actions, $\gamma$ is the discount-factor, and $\varepsilon$ is the optimality-gap) which holds \emph{uniformly} for \emph{all} domains. While the possibility of a universal bound is quite remarkable, we show that this bound is very loose. We propose a novel non-MDP abstraction which allows for a much better upper bound of $O\left(\varepsilon^{-1} \cdot (1-\gamma)^{-2} \cdot A \cdot 2^{A}\right)$. Furthermore, we show that this bound can be improved further to $O\left(\varepsilon^{-1} \cdot (1-\gamma)^{-2} \cdot \log^3 A \right)$ by using an action-sequentialization method.

For its advantage in GPU acceleration and less dependency on human experts, machine learning has been an emerging tool for solving the placement and routing problems, as two critical steps in modern chip design flow. Being still in its early stage, there are fundamental issues: scalability, reward design, and end-to-end learning paradigm etc. To achieve end-to-end placement learning, we first propose a joint learning method termed by DeepPlace for the placement of macros and standard cells, by the integration of reinforcement learning with a gradient based optimization scheme. To further bridge the placement with the subsequent routing task, we also develop a joint learning approach via reinforcement learning to fulfill both macro placement and routing, which is called DeepPR. One key design in our (reinforcement) learning paradigm involves a multi-view embedding model to encode both global graph level and local node level information of the input macros. Moreover, the random network distillation is devised to encourage exploration. Experiments on public chip design benchmarks show that our method can effectively learn from experience and also provides intermediate placement for the post standard cell placement, within few hours for training.

Urban planning refers to the efforts of designing land-use configurations given a region. However, to obtain effective urban plans, urban experts have to spend much time and effort analyzing sophisticated planning constraints based on domain knowledge and personal experiences. To alleviate the heavy burden of them and produce consistent urban plans, we want to ask that can AI accelerate the urban planning process, so that human planners only adjust generated configurations for specific needs? The recent advance of deep generative models provides a possible answer, which inspires us to automate urban planning from an adversarial learning perspective. However, three major challenges arise: 1) how to define a quantitative land-use configuration? 2) how to automate configuration planning? 3) how to evaluate the quality of a generated configuration? In this paper, we systematically address the three challenges. Specifically, 1) We define a land-use configuration as a longitude-latitude-channel tensor. 2) We formulate the automated urban planning problem into a task of deep generative learning. The objective is to generate a configuration tensor given the surrounding contexts of a target region. 3) We provide quantitative evaluation metrics and conduct extensive experiments to demonstrate the effectiveness of our framework.

Recently, deep reinforcement learning (RL) has proven its feasibility in solving combinatorial optimization problems (COPs). The learning-to-rank techniques have been studied in the field of information retrieval. While several COPs can be formulated as the prioritization of input items, as is common in the information retrieval, it has not been fully explored how the learning-to-rank techniques can be incorporated into deep RL for COPs. In this paper, we present the learning-to-rank distillation-based COP framework, where a high-performance ranking policy obtained by RL for a COP can be distilled into a non-iterative, simple model, thereby achieving a low-latency COP solver. Specifically, we employ the approximated ranking distillation to render a score-based ranking model learnable via gradient descent. Furthermore, we use the efficient sequence sampling to improve the inference performance with a limited delay. With the framework, we demonstrate that a distilled model not only achieves comparable performance to its respective, high-performance RL, but also provides several times faster inferences. We evaluate the framework with several COPs such as priority-based task scheduling and multidimensional knapsack, demonstrating the benefits of the framework in terms of inference latency and performance.

We study the problem of policy evaluation with linear function approximation and present efficient and practical algorithms that come with strong optimality guarantees. We begin by proving lower bounds that establish baselines on both the deterministic error and stochastic error in this problem. In particular, we prove an oracle complexity lower bound on the deterministic error in an instance-dependent norm associated with the stationary distribution of the transition kernel, and use the local asymptotic minimax machinery to prove an instance-dependent lower bound on the stochastic error in the i.i.d. observation model. Existing algorithms fail to match at least one of these lower bounds: To illustrate, we analyze a variance-reduced variant of temporal difference learning, showing in particular that it fails to achieve the oracle complexity lower bound. To remedy this issue, we develop an accelerated, variance-reduced fast temporal difference algorithm (VRFTD) that simultaneously matches both lower bounds and attains a strong notion of instance-optimality. Finally, we extend the VRFTD algorithm to the setting with Markovian observations, and provide instance-dependent convergence results that match those in the i.i.d. setting up to a multiplicative factor that is proportional to the mixing time of the chain. Our theoretical guarantees of optimality are corroborated by numerical experiments.

In this effort we consider a reinforcement learning (RL) technique for solving personalization tasks with complex reward signals. In particular, our approach is based on state space clustering with the use of a simplistic $k$-means algorithm as well as conventional choices of the network architectures and optimization algorithms. Numerical examples demonstrate the efficiency of different RL procedures and are used to illustrate that this technique accelerates the agent's ability to learn and does not restrict the agent's performance.

Although deep reinforcement learning has become a promising machine learning approach for sequential decision-making problems, it is still not mature enough for high-stake domains such as autonomous driving or medical applications. In such contexts, a learned policy needs for instance to be interpretable, so that it can be inspected before any deployment (e.g., for safety and verifiability reasons). This survey provides an overview of various approaches to achieve higher interpretability in reinforcement learning (RL). To that aim, we distinguish interpretability (as a property of a model) and explainability (as a post-hoc operation, with the intervention of a proxy) and discuss them in the context of RL with an emphasis on the former notion. In particular, we argue that interpretable RL may embrace different facets: interpretable inputs, interpretable (transition/reward) models, and interpretable decision-making. Based on this scheme, we summarize and analyze recent work related to interpretable RL with an emphasis on papers published in the past 10 years. We also discuss briefly some related research areas and point to some potential promising research directions.

In this paper, we propose a quantized learning equation with a monotone increasing resolution of quantization and stochastic analysis for the proposed algorithm. According to the white noise hypothesis for the quantization error with dense and uniform distribution, we can regard the quantization error as i.i.d.\ white noise. Based on this, we show that the learning equation with monotonically increasing quantization resolution converges weakly as the distribution viewpoint. The analysis of this paper shows that global optimization is possible for a domain that satisfies the Lipschitz condition instead of local convergence properties such as the Hessian constraint of the objective function.

Road maintenance planning is an integral part of road asset management. One of the main challenges in Maintenance and Rehabilitation (M&R) practices is to determine maintenance type and timing. This research proposes a framework using Reinforcement Learning (RL) based on the Long Term Pavement Performance (LTPP) database to determine the type and timing of M&R practices. A predictive DNN model is first developed in the proposed algorithm, which serves as the Environment for the RL algorithm. For the Policy estimation of the RL model, both DQN and PPO models are developed. However, PPO has been selected in the end due to better convergence and higher sample efficiency. Indicators used in this study are International Roughness Index (IRI) and Rutting Depth (RD). Initially, we considered Cracking Metric (CM) as the third indicator, but it was then excluded due to the much fewer data compared to other indicators, which resulted in lower accuracy of the results. Furthermore, in cost-effectiveness calculation (reward), we considered both the economic and environmental impacts of M&R treatments. Costs and environmental impacts have been evaluated with paLATE 2.0 software. Our method is tested on a hypothetical case study of a six-lane highway with 23 kilometers length located in Texas, which has a warm and wet climate. The results propose a 20-year M&R plan in which road condition remains in an excellent condition range. Because the early state of the road is at a good level of service, there is no need for heavy maintenance practices in the first years. Later, after heavy M&R actions, there are several 1-2 years of no need for treatments. All of these show that the proposed plan has a logical result. Decision-makers and transportation agencies can use this scheme to conduct better maintenance practices that can prevent budget waste and, at the same time, minimize the environmental impacts.