We introduce Lemur and Lemur-Chat, openly accessible language models optimized for both natural language and coding capabilities to serve as the backbone of versatile language agents. The evolution from language chat models to functional language agents demands that models not only master human interaction, reasoning, and planning but also ensure grounding in the relevant environments. This calls for a harmonious blend of language and coding capabilities in the models. Lemur and Lemur-Chat are proposed to address this necessity, demonstrating balanced proficiencies in both domains, unlike existing open-source models that tend to specialize in either. Through meticulous pre-training using a code-intensive corpus and instruction fine-tuning on text and code data, our models achieve state-of-the-art averaged performance across diverse text and coding benchmarks among open-source models. Comprehensive experiments demonstrate Lemur's superiority over existing open-source models and its proficiency across various agent tasks involving human communication, tool usage, and interaction under fully- and partially- observable environments. The harmonization between natural and programming languages enables Lemur-Chat to significantly narrow the gap with proprietary models on agent abilities, providing key insights into developing advanced open-source agents adept at reasoning, planning, and operating seamlessly across environments. https://github.com/OpenLemur/Lemur

This paper concerns imitation learning (IL) (i.e, the problem of learning to mimic expert behaviors from demonstrations) in cooperative multi-agent systems. The learning problem under consideration poses several challenges, characterized by high-dimensional state and action spaces and intricate inter-agent dependencies. In a single-agent setting, IL has proven to be done efficiently through an inverse soft-Q learning process given expert demonstrations. However, extending this framework to a multi-agent context introduces the need to simultaneously learn both local value functions to capture local observations and individual actions, and a joint value function for exploiting centralized learning. In this work, we introduce a novel multi-agent IL algorithm designed to address these challenges. Our approach enables the centralized learning by leveraging mixing networks to aggregate decentralized Q functions. A main advantage of this approach is that the weights of the mixing networks can be trained using information derived from global states. We further establish conditions for the mixing networks under which the multi-agent objective function exhibits convexity within the Q function space. We present extensive experiments conducted on some challenging competitive and cooperative multi-agent game environments, including an advanced version of the Star-Craft multi-agent challenge (i.e., SMACv2), which demonstrates the effectiveness of our proposed algorithm compared to existing state-of-the-art multi-agent IL algorithms.

Multi-agent reinforcement learning (MARL) has achieved re markable empirical successes in solving complicated games involving sequential and strategic d ecision-making across multiple agents ( Vinyals et al., 2019; Brown and Sandholm, 2018; Silver et al., 2016). These achievements have catalyzed many research efforts focusing on developing efficient MARL algorithms in a theoretically principled manner. Specifically, a multi-agent system is ty pically modeled as a general-sum Markov Game (MG) ( Littman, 1994), with the primary aim of efficiently discerning a certain equ ilibrium notion among multiple agents from data collected via online interactions. Some popular equilibrium notions include Nash equilibrium (NE), correlated equ ilibrium (CE), and coarse correlated equilibrium (CCE). However, multi-agent general-sum Markov Games (MGs) bring forth various challenges. In particular, empirical application suffers from the large st ate space. Such a challenge necessitates the use of the function approximation as an effective way to ex tract the essential features of RL problems and avoid dealing directly with the large state spa ce. Yet, adopting function approximation in a general-sum MG brings about additional complexities no t found in single-agent RL or a zero-sum MG.

At present, most surface-quality prediction methods can only perform single-task prediction which results in under-utilised datasets, repetitive work and increased experimental costs. To counter this, the authors propose a Bayesian hierarchical model to predict surface-roughness measurements for a turning machining process. The hierarchical model is compared to multiple independent Bayesian linear regression models to showcase the benefits of partial pooling in a machining setting with respect to prediction accuracy and uncertainty quantification.

The objective is to find the optimal state vector that minimizes the measurement error between the estimated pose and environmental landmarks. Most SLAM algorithms are passive, i.e., the robot is controlled manually and the navigation or path planning algorithm does not actively take part in robot motion or trajectory. Active SLAM (A-SLAM), however, tries to solve the optimal exploration problem of the unknown environment by proposing a navigation strategy that generates future goal/target positions actions which decrease map and pose uncertainties, thus enabling a fully autonomous navigation and mapping SLAM system without the need of an external controller or human effort. In Active Collaborative SLAM (AC-SLAM) multiple robots interchange information to improve their localization estimation and map accuracy to achieve some high-level tasks such as exploration. The exchanged information can be localization information [1], entropy [2], visual features [3], and frontier points [4]. In this article, we present a multi-agent AC-SLAM system for efficient environment exploration using frontiers detected over an Occupancy Grid (OG) map. In particular, in this work, we aim at: 1. Extending the A-SLAM approach of [5] which uses a computationally inexpensive D-optimality criterion for utility computation to a multi-agent AC-SLAM framework.

We investigate a novel modeling approach for end-to-end neural network training using hidden Markov models (HMM) where the transition probabilities between hidden states are modeled and learned explicitly. Most contemporary sequence-to-sequence models allow for from-scratch training by summing over all possible label segmentations in a given topology. In our approach there are explicit, learnable probabilities for transitions between segments as opposed to a blank label that implicitly encodes duration statistics. We implement a GPU-based forward-backward algorithm that enables the simultaneous training of label and transition probabilities. We investigate recognition results and additionally Viterbi alignments of our models. We find that while the transition model training does not improve recognition performance, it has a positive impact on the alignment quality. The generated alignments are shown to be viable targets in state-of-the-art Viterbi trainings.

Various mobile applications that comprise dependent tasks are gaining widespread popularity and are increasingly complex. These applications often have low-latency requirements, resulting in a significant surge in demand for computing resources. With the emergence of mobile edge computing (MEC), it becomes the most significant issue to offload the application tasks onto small-scale devices deployed at the edge of the mobile network for obtaining a high-quality user experience. However, since the environment of MEC is dynamic, most existing works focusing on task graph offloading, which rely heavily on expert knowledge or accurate analytical models, fail to fully adapt to such environmental changes, resulting in the reduction of user experience. This paper investigates the task graph offloading in MEC, considering the time-varying computation capabilities of edge computing devices. To adapt to environmental changes, we model the task graph scheduling for computation offloading as a Markov Decision Process (MDP). Then, we design a deep reinforcement learning algorithm (SATA-DRL) to learn the task scheduling strategy from the interaction with the environment, to improve user experience. Extensive simulations validate that SATA-DRL is superior to existing strategies in terms of reducing average makespan and deadline violation.

Given a policy of a Markov Decision Process, we define a SafeZone as a subset of states, such that most of the policy's trajectories are confined to this subset. The quality of a SafeZone is parameterized by the number of states and the escape probability, i.e., the probability that a random trajectory will leave the subset. SafeZones are especially interesting when they have a small number of states and low escape probability. We study the complexity of finding optimal SafeZones, and show that in general, the problem is computationally hard. Our main result is a bi-criteria approximation learning algorithm with a factor of almost $2$ approximation for both the escape probability and SafeZone size, using a polynomial size sample complexity.

A good model for action-effect prediction, named environment model, is important to achieve sample-efficient decision-making policy learning in many domains like robot control, recommender systems, and patients' treatment selection. We can take unlimited trials with such a model to identify the appropriate actions so that the costs of queries in the real world can be saved. It requires the model to handle unseen data correctly, also called counterfactual data. However, standard data fitting techniques do not automatically achieve such generalization ability and commonly result in unreliable models. In this work, we introduce counterfactual-query risk minimization (CQRM) in model learning for generalizing to a counterfactual dataset queried by a specific target policy. Since the target policies can be various and unknown in policy learning, we propose an adversarial CQRM objective in which the model learns on counterfactual data queried by adversarial policies, and finally derive a tractable solution GALILEO. We also discover that adversarial CQRM is closely related to the adversarial model learning, explaining the effectiveness of the latter. We apply GALILEO in synthetic tasks and a real-world application. The results show that GALILEO makes accurate predictions on counterfactual data and thus significantly improves policies in real-world testing.

Modern time series data often display complex nonlinear dependencies along with irregular regime-switching behaviors. These features present technical challenges in modeling, inference, and in offering insightful understanding into the underlying stochastic phenomena. To tackle these challenges, we introduce a novel modeling framework known as the Deep Switching State Space Model (DS$^3$M). This framework is engineered to make accurate forecasts for such time series while adeptly identifying the irregular regimes hidden within the dynamics. These identifications not only have significant economic ramifications but also contribute to a deeper understanding of the underlying phenomena. In DS$^3$M, the architecture employs discrete latent variables to represent regimes and continuous latent variables to account for random driving factors. By melding a Recurrent Neural Network (RNN) with a nonlinear Switching State Space Model (SSSM), we manage to capture the nonlinear dependencies and irregular regime-switching behaviors, governed by a Markov chain and parameterized using multilayer perceptrons. We validate the effectiveness and regime identification capabilities of DS$^3$M through short- and long-term forecasting tests on a wide array of simulated and real-world datasets, spanning sectors such as healthcare, economics, traffic, meteorology, and energy. Experimental results reveal that DS$^3$M outperforms several state-of-the-art models in terms of forecasting accuracy, while providing meaningful regime identifications.