Effective decision-making in autonomous driving relies on accurate inference of other traffic agents' future behaviors. To achieve this, we propose an online learning-based behavior prediction model and an efficient planner for Partially Observable Markov Decision Processes (POMDPs). We develop a learning-based prediction model, enhanced with a recurrent neural memory network, to dynamically update latent belief states and infer the intentions of other agents. The model can also integrate the ego vehicle's intentions to reflect closed-loop interactions among agents, and it learns from both offline data and online interactions. For planning, we employ an option-based Monte-Carlo Tree Search (MCTS) planner, which reduces computational complexity by searching over action sequences. Inside the MCTS planner, we use predicted long-term multi-modal trajectories to approximate future updates, which eliminates iterative belief updating and improves the running efficiency. Our approach also incorporates deep Q-learning (DQN) as a search prior, which significantly improves the performance of the MCTS planner. Experimental results from simulated environments validate the effectiveness of our proposed method. The online belief update model can significantly enhance the accuracy and temporal consistency of predictions, leading to improved decision-making performance. Employing DQN as a search prior in the MCTS planner considerably boosts its performance and outperforms an imitation learning-based prior. Additionally, we show that the option-based MCTS substantially outperforms the vanilla method in terms of performance and efficiency.

To address the challenge of identifying hidden danger in substations from unstructured text, a novel dynamic analysis method is proposed. We first extract relevant information from the unstructured text, and then leverages a flexible distributed search engine built on Elastic-Search to handle the data. Following this, the hidden Markov model is employed to train the data within the engine. The Viterbi algorithm is integrated to decipher the hidden state sequences, facilitating the segmentation and labeling of entities related to hidden dangers. The final step involves using the Neo4j graph database to dynamically create a knowledge graph that visualizes hidden dangers in the substation. The effectiveness of the proposed method is demonstrated through a case analysis from a specific substation with hidden dangers revealed in the text records.

Solving partially observable Markov decision processes (POMDPs) with high dimensional and continuous observations, such as camera images, is required for many real life robotics and planning problems. Recent researches suggested machine learned probabilistic models as observation models, but their use is currently too computationally expensive for online deployment. We deal with the question of what would be the implication of using simplified observation models for planning, while retaining formal guarantees on the quality of the solution. Our main contribution is a novel probabilistic bound based on a statistical total variation distance of the simplified model. We show that it bounds the theoretical POMDP value w.r.t. original model, from the empirical planned value with the simplified model, by generalizing recent results of particle-belief MDP concentration bounds. Our calculations can be separated into offline and online parts, and we arrive at formal guarantees without having to access the costly model at all during planning, which is also a novel result. Finally, we demonstrate in simulation how to integrate the bound into the routine of an existing continuous online POMDP solver.

State-of-the-art methods for Bayesian inference in state-space models are (a) conditional sequential Monte Carlo (CSMC) algorithms; (b) sophisticated 'classical' MCMC algorithms like MALA, or mGRAD from Titsias and Papaspiliopoulos (2018, arXiv:1610.09641v3 [stat.ML]). The former propose $N$ particles at each time step to exploit the model's 'decorrelation-over-time' property and thus scale favourably with the time horizon, $T$ , but break down if the dimension of the latent states, $D$, is large. The latter leverage gradient-/prior-informed local proposals to scale favourably with $D$ but exhibit sub-optimal scalability with $T$ due to a lack of model-structure exploitation. We introduce methods which combine the strengths of both approaches. The first, Particle-MALA, spreads $N$ particles locally around the current state using gradient information, thus extending MALA to $T > 1$ time steps and $N > 1$ proposals. The second, Particle-mGRAD, additionally incorporates (conditionally) Gaussian prior dynamics into the proposal, thus extending the mGRAD algorithm to $T > 1$ time steps and $N > 1$ proposals. We prove that Particle-mGRAD interpolates between CSMC and Particle-MALA, resolving the 'tuning problem' of choosing between CSMC (superior for highly informative prior dynamics) and Particle-MALA (superior for weakly informative prior dynamics). We similarly extend other 'classical' MCMC approaches like auxiliary MALA, aGRAD, and preconditioned Crank-Nicolson-Langevin (PCNL) to $T > 1$ time steps and $N > 1$ proposals. In experiments, for both highly and weakly informative prior dynamics, our methods substantially improve upon both CSMC and sophisticated 'classical' MCMC approaches.

Multi-Agent Reinforcement Learning (MARL) comprises a broad area of research within the field of multi-agent systems. Several recent works have focused specifically on the study of communication approaches in MARL. While multiple communication methods have been proposed, these might still be too complex and not easily transferable to more practical contexts. One of the reasons for that is due to the use of the famous parameter sharing trick. In this paper, we investigate how independent learners in MARL that do not share parameters can communicate. We demonstrate that this setting might incur into some problems, to which we propose a new learning scheme as a solution. Our results show that, despite the challenges, independent agents can still learn communication strategies following our method. Additionally, we use this method to investigate how communication in MARL is affected by different network capacities, both for sharing and not sharing parameters. We observe that communication may not always be needed and that the chosen agent network sizes need to be considered when used together with communication in order to achieve efficient learning.

We seek to model a collection of time series arising from multiple entities interacting over the same time period. Recent work focused on modeling individual time series is inadequate for our intended applications, where collective system-level behavior influences the trajectories of individual entities. To address such problems, we present a new hierarchical switching-state model that can be trained in an unsupervised fashion to simultaneously explain both system-level and individual-level dynamics. We employ a latent system-level discrete state Markov chain that drives latent entity-level chains which in turn govern the dynamics of each observed time series. Feedback from the observations to the chains at both the entity and system levels improves flexibility via context-dependent state transitions. Our hierarchical switching recurrent dynamical models can be learned via closed-form variational coordinate ascent updates to all latent chains that scale linearly in the number of individual time series. This is asymptotically no more costly than fitting separate models for each entity. Experiments on synthetic and real datasets show that our model can produce better forecasts of future entity behavior than existing methods. Moreover, the availability of latent state chains at both the entity and system level enables interpretation of group dynamics.

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.