Many important behavior changes are frictionful; they require individuals to expend effort over a long period with little immediate gratification. Here, an artificial intelligence (AI) agent can provide personalized interventions to help individuals stick to their goals. In these settings, the AI agent must personalize rapidly (before the individual disengages) and interpretably, to help us understand the behavioral interventions. In this paper, we introduce Behavior Model Reinforcement Learning (BMRL), a framework in which an AI agent intervenes on the parameters of a Markov Decision Process (MDP) belonging to a boundedly rational human agent. Our formulation of the human decision-maker as a planning agent allows us to attribute undesirable human policies (ones that do not lead to the goal) to their maladapted MDP parameters, such as an extremely low discount factor. Furthermore, we propose a class of tractable human models that captures fundamental behaviors in frictionful tasks. Introducing a notion of MDP equivalence specific to BMRL, we theoretically and empirically show that AI planning with our human models can lead to helpful policies on a wide range of more complex, ground-truth humans.

In this paper, we study the expressivity of scalar, Markovian reward functions in Reinforcement Learning (RL), and identify several limitations to what they can express. Specifically, we look at three classes of RL tasks; multi-objective RL, risk-sensitive RL, and modal RL. For each class, we derive necessary and sufficient conditions that describe when a problem in this class can be expressed using a scalar, Markovian reward. Moreover, we find that scalar, Markovian rewards are unable to express most of the instances in each of these three classes. We thereby contribute to a more complete understanding of what standard reward functions can and cannot express. In addition to this, we also call attention to modal problems as a new class of problems, since they have so far not been given any systematic treatment in the RL literature. We also briefly outline some approaches for solving some of the problems we discuss, by means of bespoke RL algorithms.

Markov processes are widely used mathematical models for describing dynamic systems in various fields. However, accurately simulating large-scale systems at long time scales is computationally expensive due to the short time steps required for accurate integration. In this paper, we introduce an inference process that maps complex systems into a simplified representational space and models large jumps in time. To achieve this, we propose Time-lagged Information Bottleneck (T-IB), a principled objective rooted in information theory, which aims to capture relevant temporal features while discarding high-frequency information to simplify the simulation task and minimize the inference error. Our experiments demonstrate that T-IB learns information-optimal representations for accurately modeling the statistical properties and dynamics of the original process at a selected time lag, outperforming existing time-lagged dimensionality reduction methods.

Controlling energy consumption in buildings through demand response (DR) has become increasingly important to reduce global carbon emissions and limit climate change. In this paper, we specifically focus on controlling the heating system of a residential building to optimize its energy consumption while respecting user's thermal comfort. Recent works in this area have mainly focused on either model-based control, e.g., model predictive control (MPC), or model-free reinforcement learning (RL) to implement practical DR algorithms. A specific RL method that recently has achieved impressive success in domains such as board games (go, chess) is Monte Carlo Tree Search (MCTS). Yet, for building control it has remained largely unexplored. Thus, we study MCTS specifically for building demand response. Its natural structure allows a flexible optimization that implicitly integrate exogenous constraints (as opposed, for example, to conventional RL solutions), making MCTS a promising candidate for DR control problems. We demonstrate how to improve MCTS control performance by incorporating a Physics-informed Neural Network (PiNN) model for its underlying thermal state prediction, as opposed to traditional purely data-driven Black-Box approaches. Our MCTS implementation aligned with a PiNN model is able to obtain a 3% increment of the obtained reward compared to a rule-based controller; leading to a 10% cost reduction and 35% reduction on temperature difference with the desired one when applied to an artificial price profile. We further implemented a Deep Learning layer into the Monte Carlo Tree Search technique using a neural network that leads the tree search through more optimal nodes. We then compared this addition with its Vanilla version, showing the improvement in computational cost required.

Major depressive disorder (MDD) presents challenges in diagnosis and treatment due to its complex and heterogeneous nature. Emerging evidence indicates that reward processing abnormalities may serve as a behavioral marker for MDD. To measure reward processing, patients perform computer-based behavioral tasks that involve making choices or responding to stimulants that are associated with different outcomes. Reinforcement learning (RL) models are fitted to extract parameters that measure various aspects of reward processing to characterize how patients make decisions in behavioral tasks. Recent findings suggest the inadequacy of characterizing reward learning solely based on a single RL model; instead, there may be a switching of decision-making processes between multiple strategies. An important scientific question is how the dynamics of learning strategies in decision-making affect the reward learning ability of individuals with MDD. Motivated by the probabilistic reward task (PRT) within the EMBARC study, we propose a novel RL-HMM framework for analyzing reward-based decision-making. Our model accommodates learning strategy switching between two distinct approaches under a hidden Markov model (HMM): subjects making decisions based on the RL model or opting for random choices. We account for continuous RL state space and allow time-varying transition probabilities in the HMM. We introduce a computationally efficient EM algorithm for parameter estimation and employ a nonparametric bootstrap for inference. We apply our approach to the EMBARC study to show that MDD patients are less engaged in RL compared to the healthy controls, and engagement is associated with brain activities in the negative affect circuitry during an emotional conflict task.

Stochastic Approximation (SA) is a widely used algorithmic approach in various fields, including optimization and reinforcement learning (RL). Among RL algorithms, Q-learning is particularly popular due to its empirical success. In this paper, we study asynchronous Q-learning with constant stepsize, which is commonly used in practice for its fast convergence. By connecting the constant stepsize Q-learning to a time-homogeneous Markov chain, we show the distributional convergence of the iterates in Wasserstein distance and establish its exponential convergence rate. We also establish a Central Limit Theory for Q-learning iterates, demonstrating the asymptotic normality of the averaged iterates. Moreover, we provide an explicit expansion of the asymptotic bias of the averaged iterate in stepsize. Specifically, the bias is proportional to the stepsize up to higher-order terms and we provide an explicit expression for the linear coefficient. This precise characterization of the bias allows the application of Richardson-Romberg (RR) extrapolation technique to construct a new estimate that is provably closer to the optimal Q function. Numerical results corroborate our theoretical finding on the improvement of the RR extrapolation method.

The age of information (AoI) is used to measure the freshness of the data. In IoT networks, the traditional resource management schemes rely on a message exchange between the devices and the base station (BS) before communication which causes high AoI, high energy consumption, and low reliability. Unmanned aerial vehicles (UAVs) as flying BSs have many advantages in minimizing the AoI, energy-saving, and throughput improvement. In this paper, we present a novel learning-based framework that estimates the traffic arrival of IoT devices based on Markovian events. The learning proceeds to optimize the trajectory of multiple UAVs and their scheduling policy. First, the BS predicts the future traffic of the devices. We compare two traffic predictors: the forward algorithm (FA) and the long short-term memory (LSTM). Afterward, we propose a deep reinforcement learning (DRL) approach to optimize the optimal policy of each UAV. Finally, we manipulate the optimum reward function for the proposed DRL approach. Simulation results show that the proposed algorithm outperforms the random-walk (RW) baseline model regarding the AoI, scheduling accuracy, and transmission power.

Autonomous agents capable of planning, reasoning, and executing actions on the web offer a promising avenue for automating computer tasks. However, the majority of existing benchmarks primarily focus on text-based agents, neglecting many natural tasks that require visual information to effectively solve. Given that most computer interfaces cater to human perception, visual information often augments textual data in ways that text-only models struggle to harness effectively. To bridge this gap, we introduce VisualWebArena, a benchmark designed to assess the performance of multimodal web agents on realistic \textit{visually grounded tasks}. VisualWebArena comprises of a set of diverse and complex web-based tasks that evaluate various capabilities of autonomous multimodal agents. To perform on this benchmark, agents need to accurately process image-text inputs, interpret natural language instructions, and execute actions on websites to accomplish user-defined objectives. We conduct an extensive evaluation of state-of-the-art LLM-based autonomous agents, including several multimodal models. Through extensive quantitative and qualitative analysis, we identify several limitations of text-only LLM agents, and reveal gaps in the capabilities of state-of-the-art multimodal language agents. VisualWebArena provides a framework for evaluating multimodal autonomous language agents, and offers insights towards building stronger autonomous agents for the web. Our code, baseline models, and data is publicly available at https://jykoh.com/vwa.

Approaching robotic cloth manipulation using reinforcement learning based on visual feedback is appealing as robot perception and control can be learned simultaneously. However, major challenges result due to the intricate dynamics of cloth and the high dimensionality of the corresponding states, what shadows the practicality of the idea. To tackle these issues, we propose TraKDis, a novel Transformer-based Knowledge Distillation approach that decomposes the visual reinforcement learning problem into two distinct stages. In the first stage, a privileged agent is trained, which possesses complete knowledge of the cloth state information. This privileged agent acts as a teacher, providing valuable guidance and training signals for subsequent stages. The second stage involves a knowledge distillation procedure, where the knowledge acquired by the privileged agent is transferred to a vision-based agent by leveraging pre-trained state estimation and weight initialization. TraKDis demonstrates better performance when compared to state-of-the-art RL techniques, showing a higher performance of 21.9%, 13.8%, and 8.3% in cloth folding tasks in simulation. Furthermore, to validate robustness, we evaluate the agent in a noisy environment; the results indicate its ability to handle and adapt to environmental uncertainties effectively. Real robot experiments are also conducted to showcase the efficiency of our method in real-world scenarios.

Generative models offer a direct way of modeling complex data. Energy-based models attempt to encode the statistical correlations observed in the data at the level of the Boltzmann weight associated with an energy function in the form of a neural network. We address here the challenge of understanding the physical interpretation of such models. In this study, we propose a simple solution by implementing a direct mapping between the Restricted Boltzmann Machine and an effective Ising spin Hamiltonian. This mapping includes interactions of all possible orders, going beyond the conventional pairwise interactions typically considered in the inverse Ising (or Boltzmann Machine) approach, and allowing the description of complex datasets. Earlier works attempted to achieve this goal, but the proposed mappings were inaccurate for inference applications, did not properly treat the complexity of the problem, or did not provide precise prescriptions for practical application. To validate our method, we performed several controlled inverse numerical experiments in which we trained the RBMs using equilibrium samples of predefined models with local external fields, 2-body and 3-body interactions in different sparse topologies. The results demonstrate the effectiveness of our proposed approach in learning the correct interaction network and pave the way for its application in modeling interesting binary variable datasets. We also evaluate the quality of the inferred model based on different training methods.