VLM Q-Learning: Aligning Vision-Language Models for Interactive Decision-Making

Recent research looks to harness the general knowledge and reasoning of large language models (LLMs) into agents that accomplish user-specified goals in interactive environments. Vision-language models (VLMs) extend LLMs to multi-modal data and provide agents with the visual reasoning necessary for new applications in areas such as computer automation. However, agent tasks emphasize skills where accessible open-weight VLMs lag behind their LLM equivalents. For example, VLMs are less capable of following an environment's strict output syntax requirements and are more focused on open-ended question answering. Overcoming these limitations requires supervised fine-tuning (SFT) on task-specific expert demonstrations. Our work approaches these challenges from an offline-to-online reinforcement learning (RL) perspective. RL lets us fine-tune VLMs to agent tasks while learning from the unsuccessful decisions of our own model or more capable (larger) models. We explore an off-policy RL solution that retains the stability and simplicity of the widely used SFT workflow while allowing our agent to self-improve and learn from low-quality datasets. We demonstrate this technique with two open-weight VLMs across three multi-modal agent domains.

Exploring Equity of Climate Policies using Multi-Agent Multi-Objective Reinforcement Learning

Addressing climate change requires coordinated policy efforts of nations worldwide. These efforts are informed by scientific reports, which rely in part on Integrated Assessment Models (IAMs), prominent tools used to assess the economic impacts of climate policies. However, traditional IAMs optimize policies based on a single objective, limiting their ability to capture the trade-offs among economic growth, temperature goals, and climate justice. As a result, policy recommendations have been criticized for perpetuating inequalities, fueling disagreements during policy negotiations. We introduce Justice, the first framework integrating IAM with Multi-Objective Multi-Agent Reinforcement Learning (MOMARL). By incorporating multiple objectives, Justice generates policy recommendations that shed light on equity while balancing climate and economic goals. Further, using multiple agents can provide a realistic representation of the interactions among the diverse policy actors. We identify equitable Pareto-optimal policies using our framework, which facilitates deliberative decision-making by presenting policymakers with the inherent trade-offs in climate and economic policy.

Multi-Goal Dexterous Hand Manipulation using Probabilistic Model-based Reinforcement Learning

This paper tackles the challenge of learning multi-goal dexterous hand manipulation tasks using model-based Reinforcement Learning. We propose Goal-Conditioned Probabilistic Model Predictive Control (GC-PMPC) by designing probabilistic neural network ensembles to describe the high-dimensional dexterous hand dynamics and introducing an asynchronous MPC policy to meet the control frequency requirements in real-world dexterous hand systems. Extensive evaluations on four simulated Shadow Hand manipulation scenarios with randomly generated goals demonstrate GC-PMPC's superior performance over state-of-the-art baselines. It successfully drives a cable-driven Dexterous hand, DexHand 021 with 12 Active DOFs and 5 tactile sensors, to learn manipulating a cubic die to three goal poses within approximately 80 minutes of interactions, demonstrating exceptional learning efficiency and control performance on a cost-effective dexterous hand platform.

Integration of Multi-Mode Preference into Home Energy Management System Using Deep Reinforcement Learning

Home Energy Management Systems (HEMS) have emerged as a pivotal tool in the smart home ecosystem, aiming to enhance energy efficiency, reduce costs, and improve user comfort. By enabling intelligent control and optimization of household energy consumption, HEMS plays a significant role in bridging the gap between consumer needs and energy utility objectives. However, much of the existing literature construes consumer comfort as a mere deviation from the standard appliance settings. Such deviations are typically incorporated into optimization objectives via static weighting factors. These factors often overlook the dynamic nature of consumer behaviors and preferences. Addressing this oversight, our paper introduces a multi-mode Deep Reinforcement Learning-based HEMS (DRL-HEMS) framework, meticulously designed to optimize based on dynamic, consumer-defined preferences. Our primary goal is to augment consumer involvement in Demand Response (DR) programs by embedding dynamic multi-mode preferences tailored to individual appliances. In this study, we leverage a model-free, single-agent DRL algorithm to deliver a HEMS framework that is not only dynamic but also user-friendly. To validate its efficacy, we employed real-world data at 15-minute intervals, including metrics such as electricity price, ambient temperature, and appliances' power consumption. Our results show that the model performs exceptionally well in optimizing energy consumption within different preference modes. Furthermore, when compared to traditional algorithms based on Mixed-Integer Linear Programming (MILP), our model achieves nearly optimal performance while outperforming in computational efficiency.

Towards Efficient Online Tuning of VLM Agents via Counterfactual Soft Reinforcement Learning

Online fine-tuning vision-language model (VLM) agents with reinforcement learning (RL) has shown promise for equipping agents with multi-step, goal-oriented capabilities in dynamic environments. However, their open-ended textual action space and non-end-to-end nature of action generation present significant challenges to effective online exploration in RL, e.g., explosion of the exploration space. We propose a novel online fine-tuning method, Counterfactual Soft Reinforcement Learning (CoSo), better suited to the textual output space of VLM agents. Compared to prior methods that assign uniform uncertainty to all tokens, CoSo leverages counterfactual reasoning to dynamically assess the causal influence of individual tokens on post-processed actions. By prioritizing the exploration of action-critical tokens while reducing the impact of semantically redundant or low-impact tokens, CoSo enables a more targeted and efficient online rollout process. We provide theoretical analysis proving CoSo's convergence and policy improvement guarantees, and extensive empirical evaluations supporting CoSo's effectiveness. Our results across a diverse set of agent tasks, including Android device control, card gaming, and embodied AI, highlight its remarkable ability to enhance exploration efficiency and deliver consistent performance gains. The code is available at https://github.com/langfengQ/CoSo.

Hierarchical Reinforcement Learning in Multi-Goal Spatial Navigation with Autonomous Mobile Robots

Hierarchical reinforcement learning (HRL) is hypothesized to be able to take advantage of the inherent hierarchy in robot learning tasks with sparse reward schemes, in contrast to more traditional reinforcement learning algorithms. In this research, hierarchical reinforcement learning is evaluated and contrasted with standard reinforcement learning in complex navigation tasks. We evaluate unique characteristics of HRL, including their ability to create sub-goals and the termination function. We constructed experiments to test the differences between PPO and HRL, different ways of creating sub-goals, manual vs automatic sub-goal creation, and the effects of the frequency of termination on performance. These experiments highlight the advantages of HRL and how it achieves these advantages.

Recursive Deep Inverse Reinforcement Learning

Inferring an adversary's goals from exhibited behavior is crucial for counterplanning and non-cooperative multi-agent systems in domains like cybersecurity, military, and strategy games. Deep Inverse Reinforcement Learning (IRL) methods based on maximum entropy principles show promise in recovering adversaries' goals but are typically offline, require large batch sizes with gradient descent, and rely on first-order updates, limiting their applicability in real-time scenarios. We propose an online Recursive Deep Inverse Reinforcement Learning (RDIRL) approach to recover the cost function governing the adversary actions and goals. Specifically, we minimize an upper bound on the standard Guided Cost Learning (GCL) objective using sequential second-order Newton updates, akin to the Extended Kalman Filter (EKF), leading to a fast (in terms of convergence) learning algorithm. We demonstrate that RDIRL is able to recover cost and reward functions of expert agents in standard and adversarial benchmark tasks. Experiments on benchmark tasks show that our proposed approach outperforms several leading IRL algorithms.

Next-Future: Sample-Efficient Policy Learning for Robotic-Arm Tasks

Hindsight Experience Replay (HER) is widely regarded as the state-of-the-art algorithm for achieving sample-efficient multi-goal reinforcement learning (RL) in robotic manipulation tasks with binary rewards. HER facilitates learning from failed attempts by replaying trajectories with redefined goals. However, it relies on a heuristic-based replay method that lacks a principled framework. To address this limitation, we introduce a novel replay strategy, "Next-Future", which focuses on rewarding single-step transitions. This approach significantly enhances sample efficiency and accuracy in learning multi-goal Markov decision processes (MDPs), particularly under stringent accuracy requirements -- a critical aspect for performing complex and precise robotic-arm tasks. We demonstrate the efficacy of our method by highlighting how single-step learning enables improved value approximation within the multi-goal RL framework. The performance of the proposed replay strategy is evaluated across eight challenging robotic manipulation tasks, using ten random seeds for training. Our results indicate substantial improvements in sample efficiency for seven out of eight tasks and higher success rates in six tasks. Furthermore, real-world experiments validate the practical feasibility of the learned policies, demonstrating the potential of "Next-Future" in solving complex robotic-arm tasks.

Solving Multi-Agent Safe Optimal Control with Distributed Epigraph Form MARL

Tasks for multi-robot systems often require the robots to collaborate and complete a team goal while maintaining safety. This problem is usually formalized as a constrained Markov decision process (CMDP), which targets minimizing a global cost and bringing the mean of constraint violation below a user-defined threshold. Inspired by real-world robotic applications, we define safety as zero constraint violation. While many safe multi-agent reinforcement learning (MARL) algorithms have been proposed to solve CMDPs, these algorithms suffer from unstable training in this setting. To tackle this, we use the epigraph form for constrained optimization to improve training stability and prove that the centralized epigraph form problem can be solved in a distributed fashion by each agent. This results in a novel centralized training distributed execution MARL algorithm named Def-MARL. Simulation experiments on 8 different tasks across 2 different simulators show that Def-MARL achieves the best overall performance, satisfies safety constraints, and maintains stable training. Real-world hardware experiments on Crazyflie quadcopters demonstrate the ability of Def-MARL to safely coordinate agents to complete complex collaborative tasks compared to other methods.

Towards More Efficient, Robust, Instance-adaptive, and Generalizable Online Learning

The primary goal of my Ph.D. study is to develop provably efficient and practical algorithms for data-driven online sequential decision-making under uncertainty. My work focuses on reinforcement learning (RL), multi-armed bandits, and their applications, including recommendation systems, computer networks, video analytics, and large language models (LLMs). Online learning methods, such as bandits and RL, have demonstrated remarkable success - ranging from outperforming human players in complex games like Atari and Go to advancing robotics, recommendation systems, and fine-tuning LLMs. Despite these successes, many established algorithms rely on idealized models that can fail under model misspecifications or adversarial perturbations, particularly in settings where accurate prior knowledge of the underlying model class is unavailable or where malicious users operate within dynamic systems. These challenges are pervasive in real-world applications, where robust and adaptive solutions are critical. Furthermore, while worst-case guarantees provide theoretical reliability, they often fail to capture instance-dependent performance, which can lead to more efficient and practical solutions. Another key challenge lies in generalizing to new, unseen environments, a crucial requirement for deploying these methods in dynamic and unpredictable settings. To address these limitations, my research aims to develop more efficient, robust, instance-adaptive, and generalizable online learning algorithms for both reinforcement learning and bandits. Towards this end, I focus on developing more efficient, robust, instance-adaptive, and generalizable for both general reinforcement learning (RL) and bandits.