Imitation learning typically performs training and testing in the same environment. This is by necessity as the Markov Decision Process(MDP) formalism defines a policy on a particular state space. However, real world environments are rarely so cleanly defined and benign changes to the environment can induce a completely new state space. Although deep imitation learning (Ho and Ermon, 2016) still defines a policy on unseen states, it remains extremely difficult to effectively generalize (Duan et al., 2017). Domain adaptation addresses how to generalize a policy defined in a source domain to perform the same task in a target domain (Higgins et al., 2017).

In this dissertation, we cover some recent advances in collaborative filtering and ranking. In chapter 1, we give a brief introduction of the history and the current landscape of collaborative filtering and ranking; chapter 2 we first talk about pointwise collaborative filtering problem with graph information, and how our proposed new method can encode very deep graph information which helps four existing graph collaborative filtering algorithms; chapter 3 is on the pairwise approach for collaborative ranking and how we speed up the algorithm to near-linear time complexity; chapter 4 is on the new listwise approach for collaborative ranking and how the listwise approach is a better choice of loss for both explicit and implicit feedback over pointwise and pairwise loss; chapter 5 is about the new regularization technique Stochastic Shared Embeddings (SSE) we proposed for embedding layers and how it is both theoretically sound and empirically effectively for 6 different tasks across recommendation and natural language processing; chapter 6 is how we introduce personalization for the state-of-the-art sequential recommendation model with the help of SSE, which plays an important role in preventing our personalized model from overfitting to the training data; chapter 7, we summarize what we have achieved so far and predict what the future directions can be; chapter 8 is the appendix to all the chapters.

This work exploits action equivariance for representation learning in reinforcement learning. Equivariance under actions states that transitions in the input space are mirrored by equivalent transitions in latent space, while the map and transition functions should also commute. We introduce a contrastive loss function that enforces action equivariance on the learned representations. We prove that when our loss is zero, we have a homomorphism of a deterministic Markov Decision Process (MDP). Learning equivariant maps leads to structured latent spaces, allowing us to build a model on which we plan through value iteration. We show experimentally that for deterministic MDPs, the optimal policy in the abstract MDP can be successfully lifted to the original MDP. Moreover, the approach easily adapts to changes in the goal states. Empirically, we show that in such MDPs, we obtain better representations in fewer epochs compared to representation learning approaches using reconstructions, while generalizing better to new goals than model-free approaches.

We study the estimation of risk-sensitive policies in reinforcement learning problems defined by a Markov Decision Process (MDPs) whose state and action spaces are countably finite. Prior efforts are predominately afflicted by computational challenges associated with the fact that risk-sensitive MDPs are time-inconsistent. To ameliorate this issue, we propose a new definition of risk, which we call caution, as a penalty function added to the dual objective of the linear programming (LP) formulation of reinforcement learning. The caution measures the distributional risk of a policy, which is a function of the policy's long-term state occupancy distribution. To solve this problem in an online model-free manner, we propose a stochastic variant of primal-dual method that uses Kullback-Lieber (KL) divergence as its proximal term. We establish that the number of iterations/samples required to attain approximately optimal solutions of this scheme matches tight dependencies on the cardinality of the state and action spaces, but differs in its dependence on the infinity norm of the gradient of the risk measure. Experiments demonstrate the merits of this approach for improving the reliability of reward accumulation without additional computational burdens.

This paper presents a novel approach for temporal modelling of long-term human activities based on wavelet transforms. The model is applied to binary smart-home sensors to forecast their signals, which are used then as temporal priors to infer anomalies in office and Active & Assisted Living (AAL) scenarios. Such inference is performed by a new extension of Hybrid Markov Logic Networks (HMLNs) that merges different anomaly indicators, including activity levels detected by sensors, expert rules and the new temporal models. The latter in particular allow the inference system to discover deviations from long-term activity patterns, which cannot by detected by simpler frequency-based models. Two new publicly available datasets were collected using several smart-sensors to evaluate the wavelet-based temporal models and their application to signal forecasting and anomaly detection. The experimental results show the effectiveness of the proposed techniques and their successful application to detect unexpected activities in office and AAL settings.

Imitation Learning (IL) is a popular paradigm for training agents to achieve complicated goals by leveraging expert behavior, rather than dealing with the hardships of designing a correct reward function. With the environment modeled as a Markov Decision Process (MDP), most of the existing IL algorithms are contingent on the availability of expert demonstrations in the same MDP as the one in which a new imitator policy is to be learned. This is uncharacteristic of many real-life scenarios where discrepancies between the expert and the imitator MDPs are common, especially in the transition dynamics function. Furthermore, obtaining expert actions may be costly or infeasible, making the recent trend towards state-only IL (where expert demonstrations constitute only states or observations) ever so promising. Building on recent adversarial imitation approaches that are motivated by the idea of divergence minimization, we present a new state-only IL algorithm in this paper. It divides the overall optimization objective into two subproblems by introducing an indirection step and solves the subproblems iteratively. We show that our algorithm is particularly effective when there is a transition dynamics mismatch between the expert and imitator MDPs, while the baseline IL methods suffer from performance degradation. To analyze this, we construct several interesting MDPs by modifying the configuration parameters for the MuJoCo locomotion tasks from OpenAI Gym 1 .

The paper surveys the topic of tensor decompositions in modern machine learning applications. It focuses on three active research topics of significant relevance for the community. After a brief review of consolidated works on multi-way data analysis, we consider the use of tensor decompositions in compressing the parameter space of deep learning models. Lastly, we discuss how tensor methods can be leveraged to yield richer adaptive representations of complex data, including structured information. The paper concludes with a discussion on interesting open research challenges.

Bayesian nonparametric space partition (BNSP) models provide a variety of strategies for partitioning a $D$-dimensional space into a set of blocks. In this way, the data points lie in the same block would share certain kinds of homogeneity. BNSP models can be applied to various areas, such as regression/classification trees, random feature construction, relational modeling, etc. In this survey, we investigate the current progress of BNSP research through the following three perspectives: models, which review various strategies for generating the partitions in the space and discuss their theoretical foundation `self-consistency'; applications, which cover the current mainstream usages of BNSP models and their potential future practises; and challenges, which identify the current unsolved problems and valuable future research topics. As there are no comprehensive reviews of BNSP literature before, we hope that this survey can induce further exploration and exploitation on this topic.

The intelligent control of traffic signal is critical to the optimization of transportation systems. To solve the problem in large-scale road networks, recent research has focused on interactions among intersections, which have shown promising results. However, existing studies pay more attention to the sensation sharing among agents and do not care about the results after taking each action. In this paper, we propose a novel multi-agent interaction mechanism, defined as Gamma-Reward that includes both original Gamma-Reward and Gamma-Attention-Reward, which use the space-time information in the replay buffer to amend the reward of each action, for traffic signal control based on deep reinforcement learning method. We give a detailed theoretical foundation and prove the proposed method can converge to Nash Equilibrium. By extending the idea of Markov Chain to the road network, this interaction mechanism replaces the graph attention method and realizes the decoupling of the road network, which is more in line with practical applications. Simulation and experiment results demonstrate that the proposed model can get better performance than previous studies, by amending the reward. To our best knowledge, our work appears to be the first to treat the road network itself as a Markov Chain.

This paper presents the concept of an adaptive safe padding that forces Reinforcement Learning (RL) to synthesize optimal control policies while ensuring safety during the learning process. We express the safety requirements as a temporal logic formula. Enforcing the RL agent to stay safe during learning might limit the exploration in some safety-critical cases. However, we show that the proposed architecture is able to automatically handle the trade-off between efficient progress in exploration and ensuring strict safety. Theoretical guarantees are available on the convergence of the algorithm. Finally experimental results are provided to showcase the performance of the proposed method.