Integral to recent successes in deep reinforcement learning has been a class of temporal difference methods that use infrequently updated target values for policy evaluation in a Markov Decision Process. Yet a complete theoretical explanation for the effectiveness of target networks remains elusive. In this work, we provide an analysis of this popular class of algorithms, to finally answer the question: `why do target networks stabilise TD learning'? To do so, we formalise the notion of a partially fitted policy evaluation method, which describes the use of target networks and bridges the gap between fitted methods and semigradient temporal difference algorithms. Using this framework we are able to uniquely characterise the so-called deadly triad - the use of TD updates with (nonlinear) function approximation and off-policy data - which often leads to nonconvergent algorithms. This insight leads us to conclude that the use of target networks can mitigate the effects of poor conditioning in the Jacobian of the TD update. Instead, we show that under mild regularity conditions and a well tuned target network update frequency, convergence can be guaranteed even in the extremely challenging off-policy sampling and nonlinear function approximation setting.

Multi-agent pathfinding (MAPF) is a critical field in many large-scale robotic applications, often being the fundamental step in multi-agent systems. The increasing complexity of MAPF in complex and crowded environments, however, critically diminishes the effectiveness of existing solutions. In contrast to other studies that have either presented a general overview of the recent advancements in MAPF or extensively reviewed Deep Reinforcement Learning (DRL) within multi-agent system settings independently, our work presented in this review paper focuses on highlighting the integration of DRL-based approaches in MAPF. Moreover, we aim to bridge the current gap in evaluating MAPF solutions by addressing the lack of unified evaluation metrics and providing comprehensive clarification on these metrics. Finally, our paper discusses the potential of model-based DRL as a promising future direction and provides its required foundational understanding to address current challenges in MAPF. Our objective is to assist readers in gaining insight into the current research direction, providing unified metrics for comparing different MAPF algorithms and expanding their knowledge of model-based DRL to address the existing challenges in MAPF.

Reinforcement learning (RL) under changing environment models many real-world applications via nonstationary Markov Decision Processes (MDPs), and hence gains considerable interest. However, theoretical studies on nonstationary MDPs in the literature have mainly focused on tabular and linear (mixture) MDPs, which do not capture the nature of unknown representation in deep RL. In this paper, we make the first effort to investigate nonstationary RL under episodic low-rank MDPs, where both transition kernels and rewards may vary over time, and the low-rank model contains unknown representation in addition to the linear state embedding function. We first propose a parameter-dependent policy optimization algorithm called PORTAL, and further improve PORTAL to its parameter-free version of Ada-PORTAL, which is able to tune its hyper-parameters adaptively without any prior knowledge of nonstationarity. For both algorithms, we provide upper bounds on the average dynamic suboptimality gap, which show that as long as the nonstationarity is not significantly large, PORTAL and Ada-PORTAL are sample-efficient and can achieve arbitrarily small average dynamic suboptimality gap with polynomial sample complexity.

We consider the problem of time-limited robotic exploration in previously unseen environments where exploration is limited by a predefined amount of time. We propose a novel exploration approach using learning-augmented model-based planning. We generate a set of subgoals associated with frontiers on the current map and derive a Bellman Equation for exploration with these subgoals. Visual sensing and advances in semantic mapping of indoor scenes are exploited for training a deep convolutional neural network to estimate properties associated with each frontier: the expected unobserved area beyond the frontier and the expected timesteps (discretized actions) required to explore it. The proposed model-based planner is guaranteed to explore the whole scene if time permits. We thoroughly evaluate our approach on a large-scale pseudo-realistic indoor dataset (Matterport3D) with the Habitat simulator. We compare our approach with classical and more recent RL-based exploration methods. Our approach surpasses the greedy strategies by 2.1% and the RL-based exploration methods by 8.4% in terms of coverage.

Thesis concerns the study and development of hierarchical representations for spatio-temporal visual attention modeling and understanding in video sequences. More specifically, we propose two computational models for visual attention. First, we present a generative probabilistic model for context-aware visual attention modeling and understanding. Secondly, we develop a deep network architecture for visual attention modeling, which first estimates top-down spatio-temporal visual attention, and ultimately serves for modeling attention in the temporal domain. The first part of the thesis introduces our first proposal: a generative probabilistic framework for spatio-temporal visual attention modeling and understanding.

We present a novel computational model employing hierarchical active inference to simulate reading and eye movements. The model characterizes linguistic processing as inference over a hierarchical generative model, facilitating predictions and inferences at various levels of granularity, from syllables to sentences. Our approach combines the strengths of large language models for realistic textual predictions and active inference for guiding eye movements to informative textual information, enabling the testing of predictions. The model exhibits proficiency in reading both known and unknown words and sentences, adhering to the distinction between lexical and nonlexical routes in dual-route theories of reading. Notably, our model permits the exploration of maladaptive inference effects on eye movements during reading, such as in dyslexia. To simulate this condition, we attenuate the contribution of priors during the reading process, leading to incorrect inferences and a more fragmented reading style, characterized by a greater number of shorter saccades. This alignment with empirical findings regarding eye movements in dyslexic individuals highlights the model's potential to aid in understanding the cognitive processes underlying reading and eye movements, as well as how reading deficits associated with dyslexia may emerge from maladaptive predictive processing. In summary, our model represents a significant advancement in comprehending the intricate cognitive processes involved in reading and eye movements, with potential implications for understanding and addressing dyslexia through the simulation of maladaptive inference. It may offer valuable insights into this condition and contribute to the development of more effective interventions for treatment.

We present a new computing model for intrinsic rewards in reinforcement learning that addresses the limitations of existing surprise-driven explorations. The reward is the novelty of the surprise rather than the surprise norm. We estimate the surprise novelty as retrieval errors of a memory network wherein the memory stores and reconstructs surprises. Our surprise memory (SM) augments the capability of surprise-based intrinsic motivators, maintaining the agent's interest in exciting exploration while reducing unwanted attraction to unpredictable or noisy observations. Our experiments demonstrate that the SM combined with various surprise predictors exhibits efficient exploring behaviors and significantly boosts the final performance in sparse reward environments, including Noisy-TV, navigation and challenging Atari games.

This paper analyzes finite state Markov Decision Processes (MDPs) with uncertain parameters in compact sets and re-examines results from robust MDP via set-based fixed point theory. To this end, we generalize the Bellman and policy evaluation operators to contracting operators on the value function space and denote them as \emph{value operators}. We lift these value operators to act on \emph{sets} of value functions and denote them as \emph{set-based value operators}. We prove that the set-based value operators are \emph{contractions} in the space of compact value function sets. Leveraging insights from set theory, we generalize the rectangularity condition in classic robust MDP literature to a containment condition for all value operators, which is weaker and can be applied to a larger set of parameter-uncertain MDPs and contracting operators in dynamic programming. We prove that both the rectangularity condition and the containment condition sufficiently ensure that the set-based value operator's fixed point set contains its own extrema elements. For convex and compact sets of uncertain MDP parameters, we show equivalence between the classic robust value function and the supremum of the fixed point set of the set-based Bellman operator. Under dynamically changing MDP parameters in compact sets, we prove a set convergence result for value iteration, which otherwise may not converge to a single value function. Finally, we derive novel guarantees for probabilistic path-planning problems in planet exploration and stratospheric station-keeping.

In real-world scenarios, human dialogues are multi-round and diverse. Furthermore, human instructions can be unclear and human responses are unrestricted. Interactive robots face difficulties in understanding human intents and generating suitable strategies for assisting individuals through manipulation. In this article, we propose Mani-GPT, a Generative Pre-trained Transformer (GPT) for interactive robotic manipulation. The proposed model has the ability to understand the environment through object information, understand human intent through dialogues, generate natural language responses to human input, and generate appropriate manipulation plans to assist the human. This makes the human-robot interaction more natural and humanized. In our experiment, Mani-GPT outperforms existing algorithms with an accuracy of 84.6% in intent recognition and decision-making for actions. Furthermore, it demonstrates satisfying performance in real-world dialogue tests with users, achieving an average response accuracy of 70%.

There is a growing interest in using reinforcement learning (RL) to personalize sequences of treatments in digital health to support users in adopting healthier behaviors. Such sequential decision-making problems involve decisions about when to treat and how to treat based on the user's context (e.g., prior activity level, location, etc.). Online RL is a promising data-driven approach for this problem as it learns based on each user's historical responses and uses that knowledge to personalize these decisions. However, to decide whether the RL algorithm should be included in an ``optimized'' intervention for real-world deployment, we must assess the data evidence indicating that the RL algorithm is actually personalizing the treatments to its users. Due to the stochasticity in the RL algorithm, one may get a false impression that it is learning in certain states and using this learning to provide specific treatments. We use a working definition of personalization and introduce a resampling-based methodology for investigating whether the personalization exhibited by the RL algorithm is an artifact of the RL algorithm stochasticity. We illustrate our methodology with a case study by analyzing the data from a physical activity clinical trial called HeartSteps, which included the use of an online RL algorithm. We demonstrate how our approach enhances data-driven truth-in-advertising of algorithm personalization both across all users as well as within specific users in the study.