Automatic real personality recognition (RPR) aims to evaluate human real personality traits from their expressive behaviours. However, most existing solutions generally act as external observers to infer observers' personality impressions based on target individuals' expressive behaviours, which significantly deviate from their real personalities and consistently lead to inferior recognition performance. Inspired by the association between real personality and human internal cognition underlying the generation of expressive behaviours, we propose a novel RPR approach that efficiently simulates personalised internal cognition from external short audio-visual behaviours expressed by target individual. The simulated personalised cognition, represented as a set of network weights that enforce the personalised network to reproduce the individual-specific facial reactions, is further encoded as a graph containing two-dimensional node and edge feature matrices, with a novel 2D Graph Neural Network (2D-GNN) proposed for inferring real personality traits from it. To simulate real personality-related cognition, an end-to-end (E2E) strategy is designed to jointly train our cognition simulation, 2D graph construction, and personality recognition modules. Experiments show our approach’s effectiveness in capturing real personality traits with superior computational efficiency.

Standard reinforcement learning (RL) algorithms primarily focus on minimizing the expected sum of costs, which can be insufficient in contexts where risk sensitivity is crucial. This paper explores the application of a class of coherent risk measures, termed ϕ-Divergence-Risk (PhiD-R) in risk-sensitive RL. This class of risk measures not only includes established measures such as Conditional Value-at-Risk (CVaR) as special cases but also broadens the horizon for exploring new risk measures. We propose a trajectory-based policy gradient method specifically tailored for PhiD-R, applicable across all forms of risk measures formed by different ϕ-divergence. We prove the asymptotic convergence of our algorithm towards locally optimal policies using multi-time stochastic approximation techniques. Extensive simulation experiments validate the effectiveness and practicality of our approach.

Exploration is a crucial phase in reinforcement learning (RL). The reward-free RL paradigm, as explored by (Jin et al., 2020), offers an efficient method to design exploration algorithms for risk-neutral RL across various reward functions with a single exploration phase. However, as RL applications in safety critical settings grow, there’s an increasing need for risk-sensitive RL, which considers potential risks in decision-making. Yet, efficient exploration strategies for risk-sensitive RL remain underdeveloped. This study presents a novel risk-sensitive reward-free framework based on Conditional Value-at-Risk (CVaR), designed to effectively address CVaR RL for any given reward function through a single exploration phase. We introduce the CVaR-RF-UCRL algorithm, which is shown to be $(\epsilon,p)$-PAC, with a sample complexity upper bounded by $\tilde{\mathcal{O}}\left(\frac{S^2AH^4}{\epsilon^2\tau^2}\right)$ with $\tau$ being the risk tolerance parameter. We also prove a $\Omega\left(\frac{S^2AH^2}{\epsilon^2\tau}\right)$ lower bound for any CVaR-RF exploration algorithm, demonstrating the near-optimality of our algorithm. Additionally, we propose the planning algorithms: CVaR-VI and its more practical variant, CVaR-VI-DISC. The effectiveness and practicality of our CVaR reward-free approach are further validated through numerical experiments.

Robust Markov Decision Processes (RMDPs) have received significant research interest, offering an alternative to standard Markov Decision Processes (MDPs) that often assume fixed transition probabilities. RMDPs address this by optimizing for the worst-case scenarios within ambiguity sets. While earlier studies on RMDPs have largely centered on risk-neutral rein-forcement learning (RL), with the goal of minimizing expected total discounted costs, in this paper, we analyze the robustness of CVaR-based risk-sensitive RL under RMDP. Firstly, we consider predetermined ambiguity sets. Based on the coherency of CVaR, we establish a connection between robustness and risk sensitivity, thus, techniques in risk-sensitive RL can be adopted to solve the proposed problem. Furthermore, motivated by the existence of decision-dependent uncertainty in real-world problems, we study problems with state-action-dependent ambiguity sets. To solve this, we define a new risk measure named NCVaR and build the equivalence of NCVaR optimization and robust CVaR optimization. We further propose value iteration algorithms and validate our approach in simulation experiments.