We study the effect of baselines in on-policy stochastic policy gradient optimization, and close the gap between the theory and practice of policy optimization methods. Our first contribution is to show that the \emph{state value} baseline allows on-policy stochastic \emph{natural} policy gradient (NPG) to converge to a globally optimal policy at an $O(1/t)$ rate, which was not previously known. The analysis relies on two novel findings: the expected progress of the NPG update satisfies a stochastic version of the non-uniform \L{}ojasiewicz (N\L{}) inequality, and with probability 1 the state value baseline prevents the optimal action's probability from vanishing, thus ensuring sufficient exploration. Importantly, these results provide a new understanding of the role of baselines in stochastic policy gradient: by showing that the variance of natural policy gradient estimates remains unbounded with or without a baseline, we find that variance reduction \emph{cannot} explain their utility in this setting. Instead, the analysis reveals that the primary effect of the value baseline is to \textbf{reduce the aggressiveness of the updates} rather than their variance. That is, we demonstrate that a finite variance is \emph{not necessary} for almost sure convergence of stochastic NPG, while controlling update aggressiveness is both necessary and sufficient. Additional experimental results verify these theoretical findings.

HE development of autonomous vehicles (A Vs) is on the verge of passing beyond the laboratory and simulation tests and is shifting towards addressing the challenges that limit their practicality in today's society. While there is still need for further technological improvements to enable safe and smooth operation of a single A V, a great deal of research attention is being focused on the emerging challenge of operating multiple A Vs and the co-existence of A Vs and human-driven vehicles (HVs) [1], [2]. A realistic outlook for the adoption of autonomous vehicles on the roads is a mixed-traffic scenario in which human drivers with different driving styles and social preferences share the road with A Vs that are perhaps built by different manufacturers and hence follow different policies [3], [4]. In this work, we seek a solution that can ensure the safety and robustness of A Vs in the presence of human drivers with heterogeneous behavioral traits. Connected & autonomous vehicles (CA Vs) via vehicle-to-vehicle (V2V) communication allow vehicles to directly communicate with their neighbors, creating an extended perception that enables explicit coordination among vehicles to overcome the limitations of an isolated agent [5]-[11]. While planning in a fully A V scenario is relatively easy to achieve, coordination in the presence of HVs is a significantly more challenging task, as the A Vs not only need to react to road objects but also need to consider the behaviors of HVs [3], [4], [12]. We start by identifying the major challenges in the domain of behavior planning and prediction for A Vs in mixed-autonomy traffic.

Additional experimental results verify these theoretical findings.

In dynamic games with shared constraints, Generalized Nash Equilibria (GNE) are often computed using the normalized solution concept, which assumes identical Lagrange multipliers for shared constraints across all players. While widely used, this approach excludes other potentially valuable GNE. This paper addresses the limitations of normalized solutions in racing scenarios through three key contributions. First, we highlight the shortcomings of normalized solutions with a simple racing example. Second, we propose a novel method based on the Mixed Complementarity Problem (MCP) formulation to compute non-normalized Generalized Nash Equilibria (GNE). Third, we demonstrate that our proposed method overcomes the limitations of normalized GNE solutions and enables richer multi-modal interactions in realistic racing scenarios.

Counterspeech has emerged as a popular and effective strategy for combating online hate speech, sparking growing research interest in automating its generation using language models. However, the field still lacks standardised evaluation protocols and reliable automated evaluation metrics that align with human judgement. Current automatic evaluation methods, primarily based on similarity metrics, do not effectively capture the complex and independent attributes of counterspeech quality, such as contextual relevance, aggressiveness, or argumentative coherence. This has led to an increased dependency on labor-intensive human evaluations to assess automated counter-speech generation methods. To address these challenges, we introduce CSEval, a novel dataset and framework for evaluating counterspeech quality across four dimensions: contextual-relevance, aggressiveness, argument-coherence, and suitableness. Furthermore, we propose Auto-Calibrated COT for Counterspeech Evaluation (Auto-CSEval), a prompt-based method with auto-calibrated chain-of-thoughts (CoT) for scoring counterspeech using large language models. Our experiments show that Auto-CSEval outperforms traditional metrics like ROUGE, METEOR, and BertScore in correlating with human judgement, indicating a significant improvement in automated counterspeech evaluation.

Simulating realistic driving behavior is crucial for developing and testing autonomous systems in complex traffic environments. Equally important is the ability to control the behavior of simulated agents to tailor scenarios to specific research needs and safety considerations. This paper extends the general-purpose multi-agent driving behavior model ITRA (Scibior et al., 2021), by introducing a method called Control-ITRA to influence agent behavior through waypoint assignment and target speed modulation. By conditioning agents on these two aspects, we provide a mechanism for them to adhere to specific trajectories and indirectly adjust their aggressiveness. We compare different approaches for integrating these conditions during training and demonstrate that our method can generate controllable, infraction-free trajectories while preserving realism in both seen and unseen locations.

We study the effect of baselines in on-policy stochastic policy gradient optimization, and close the gap between the theory and practice of policy optimization methods. Our first contribution is to show that the \emph{state value} baseline allows on-policy stochastic \emph{natural} policy gradient (NPG) to converge to a globally optimal policy at an O(1/t) rate, which was not previously known. The analysis relies on two novel findings: the expected progress of the NPG update satisfies a stochastic version of the non-uniform \L{}ojasiewicz (N\L{}) inequality, and with probability 1 the state value baseline prevents the optimal action's probability from vanishing, thus ensuring sufficient exploration. Importantly, these results provide a new understanding of the role of baselines in stochastic policy gradient: by showing that the variance of natural policy gradient estimates remains unbounded with or without a baseline, we find that variance reduction \emph{cannot} explain their utility in this setting. Instead, the analysis reveals that the primary effect of the value baseline is to \textbf{reduce the aggressiveness of the updates} rather than their variance.

This study is the first to explore whether multi-modal large language models (LLMs) can align their behaviors with visual personas, addressing a significant gap in the literature that predominantly focuses on text-based personas. We developed a novel dataset of 5K fictional avatar images for assignment as visual personas to LLMs, and analyzed their negotiation behaviors based on the visual traits depicted in these images, with a particular focus on aggressiveness. The results indicate that LLMs assess the aggressiveness of images in a manner similar to humans and output more aggressive negotiation behaviors when prompted with an aggressive visual persona. Interestingly, the LLM exhibited more aggressive negotiation behaviors when the opponent's image appeared less aggressive than their own, and less aggressive behaviors when the opponents image appeared more aggressive.