As large language models (LLMs) are rapidly advancing and achieving near-human capabilities, aligning them with human values is becoming more urgent. In scenarios where LLMs outperform humans, we face a weak-to-strong alignment problem where we need to effectively align strong student LLMs through weak supervision generated by weak teachers. Existing alignment methods mainly focus on strong-to-weak alignment and self-alignment settings, and it is impractical to adapt them to the much harder weak-to-strong alignment setting. To fill this gap, we propose a multi-agent contrastive preference optimization (MACPO) framework. MACPO facilitates weak teachers and strong students to learn from each other by iteratively reinforcing unfamiliar positive behaviors while penalizing familiar negative ones. To get this, we devise a mutual positive behavior augmentation strategy to encourage weak teachers and strong students to learn from each other's positive behavior and further provide higher quality positive behavior for the next iteration. Additionally, we propose a hard negative behavior construction strategy to induce weak teachers and strong students to generate familiar negative behavior by fine-tuning on negative behavioral data. Experimental results on the HH-RLHF and PKU-SafeRLHF datasets, evaluated using both automatic metrics and human judgments, demonstrate that MACPO simultaneously improves the alignment performance of strong students and weak teachers. Moreover, as the number of weak teachers increases, MACPO achieves better weak-to-strong alignment performance through more iteration optimization rounds.

Recent advances in the fields of natural language processing and computer vision have shown great potential in understanding the underlying dynamics of the world from large-scale internet data. However, translating this knowledge into robotic systems remains an open challenge, given the scarcity of human-robot interactions and the lack of large-scale datasets of real-world robotic data. Previous robot learning approaches such as behavior cloning and reinforcement learning have shown great capabilities in learning robotic skills from human demonstrations or from scratch in specific environments. However, these approaches often require task-specific demonstrations or designing complex simulation environments, which limits the development of generalizable and robust policies for new settings. Aiming to address these limitations, we propose an agent-based framework for grounding robot policies to the current context, considering the constraints of a current robot and its environment using visuomotor-grounded language guidance. The proposed framework is composed of a set of conversational agents designed for specific roles--namely, high-level advisor, visual grounding, monitoring, and robotic agents. Given a base policy, the agents collectively generate guidance at run time to shift the action distribution of the base policy towards more desirable future states. We demonstrate that our approach can effectively guide manipulation policies to achieve significantly higher success rates both in simulation and in real-world experiments without the need for additional human demonstrations or extensive exploration. In recent years, the advent of foundation models, such as large-scale pre-trained language models (LLMs) and visual language models (VLMs), has shown great capabilities in understanding context, scenes, and the underlying dynamics of the world. Furthermore, emergent capabilities such as incontext learning have shown great potential in the transfer of knowledge between domains, e.g., via few-shot demonstrations or zero-shot inference.

Tool-augmented LLMs are a promising approach to create AI agents that can have realistic conversations, follow procedures, and call appropriate functions. However, evaluating them is challenging due to the diversity of possible conversations, and existing datasets focus only on single interactions and function-calling. We present a test generation pipeline to evaluate LLMs as conversational AI agents. Our framework uses LLMs to generate diverse tests grounded on user-defined procedures. For that, we use intermediate graphs to limit the LLM test generator's tendency to hallucinate content that is not grounded on input procedures, and enforces high coverage of the possible conversations. Additionally, we put forward ALMITA, a manually curated dataset for evaluating AI agents in customer support, and use it to evaluate existing LLMs. Our results show that while tool-augmented LLMs perform well in single interactions, they often struggle to handle complete conversations. While our focus is on customer support, our method is general and capable of AI agents for different domains.

Multi-agent reinforcement learning (MARL) presents unique challenges as agents learn strategies through experiences. Gradient-based methods are often sensitive to hyperparameter selection and initial random seed variations. Concurrently, significant advances have been made in solving Variational Inequalities (VIs) which include equilibrium-finding problems particularly in addressing the non-converging rotational dynamics that impede convergence of traditional gradient based optimization methods. This paper explores the potential of leveraging VI-based techniques to improve MARL training. Specifically, we study the performance of VI method namely, Nested-Lookahead VI (nLA-VI) and Extragradient (EG) in enhancing the multi-agent deep deterministic policy gradient (MADDPG) algorithm. We present a VI reformulation of the actor-critic algorithm for both single- and multi-agent settings. We introduce three algorithms that use nLA-VI, EG, and a combination of both, named LA-MADDPG, EG-MADDPG, and LA-EG-MADDPG, respectively. Our empirical results demonstrate that these VI-based approaches yield significant performance improvements in benchmark environments, such as the zero-sum games: rock-paper-scissors and matching pennies, where equilibrium strategies can be quantitatively assessed, and the Multi-Agent Particle Environment: Predator prey benchmark, where VI-based methods also yield balanced participation of agents from the same team.

Uncertainty modeling is critical in trajectory-forecasting systems for both interpretation and safety reasons. To better predict the future trajectories of multiple agents, recent works have introduced interaction modules to capture interactions among agents. This approach leads to correlations among the predicted trajectories. However, the uncertainty brought by such correlations is neglected. To fill this gap, we propose a novel concept, collaborative uncertainty (CU), which models the uncertainty resulting from the interaction module.

Each year, expert-level performance is attained in increasingly-complex multiagent domains, where notable examples include Go, Poker, and StarCraft II. This rapid progression is accompanied by a commensurate need to better understand how such agents attain this performance, to enable their safe deployment, identify limitations, and reveal potential means of improving them. In this paper we take a step back from performance-focused multiagent learning, and instead turn our attention towards agent behavior analysis. We introduce a model-agnostic method for discovery of behavior clusters in multiagent domains, using variational inference to learn a hierarchy of behaviors at the joint and local agent levels. Our framework makes no assumption about agents' underlying learning algorithms, does not require access to their latent states or policies, and is trained using only offline observational data.

Modelling the dynamics of multi-agent learning has long been an important research topic, but all of the previous works focus on 2-agent settings and mostly use evolutionary game theoretic approaches. In this paper, we study an n-agent setting with n tends to infinity, such that agents learn their policies concurrently over repeated symmetric bimatrix games with some other agents. Using mean field theory, we approximate the effects of other agents on a single agent by an averaged effect. A Fokker-Planck equation that describes the evolution of the probability distribution of Q-values in the agent population is derived. To the best of our knowledge, this is the first time to show the Q-learning dynamics under an n-agent setting can be described by a system of only three equations.

Effective coordination is crucial to solve multi-agent collaborative (MAC) problems. While centralized reinforcement learning methods can optimally solve small MAC instances, they do not scale to large problems and they fail to generalize to scenarios different from those seen during training. In this paper, we consider MAC problems with some intrinsic notion of locality (e.g., geographic proximity) such that interactions between agents and tasks are locally limited. By leveraging this property, we introduce a novel structured prediction approach to assign agents to tasks. At each step, the assignment is obtained by solving a centralized optimization problem (the inference procedure) whose objective function is parameterized by a learned scoring model.

We show for the first time that it is possible to reconcile in online learning in zero-sum games two seemingly contradictory objectives: vanishing time-average regret and non-vanishing step sizes. This phenomenon, that we coin fast and furious" learning in games, sets a new benchmark about what is possible both in max-min optimization as well as in multi-agent systems. Our analysis does not depend on introducing a carefully tailored dynamic. Instead we focus on the most well studied online dynamic, gradient descent. Similarly, we focus on the simplest textbook class of games, two-agent two-strategy zero-sum games, such as Matching Pennies. Even for this simplest of benchmarks the best known bound for total regret, prior to our work, was the trivial one of O(T), which is immediately applicable even to a non-learning agent.

Efficient exploration in deep cooperative multi-agent reinforcement learning (MARL) still remains challenging in complex coordination problems. In this paper, we introduce a novel Episodic Multi-agent reinforcement learning with Curiosity-driven exploration, called EMC. We leverage an insight of popular factorized MARL algorithms that the induced" individual Q-values, i.e., the individual utility functions used for local execution, are the embeddings of local action-observation histories, and can capture the interaction between agents due to reward backpropagation during centralized training. Therefore, we use prediction errors of individual Q-values as intrinsic rewards for coordinated exploration and utilize episodic memory to exploit explored informative experience to boost policy training. As the dynamics of an agent's individual Q-value function captures the novelty of states and the influence from other agents, our intrinsic reward can induce coordinated exploration to new or promising states.