Round-Robin Behavior Cloning (R2BC): Traditional Behavior Cloning (left) requires coordinated and centralized demonstrations, where an expert demonstrates actions near-optimally for all agents. In multi-agent domains, a lone human operator may not be able to provide high-quality demonstrations due to underactuated control and increased cognitive burden. Our method (right), R2BC, removes this restriction by letting the human control one agent at a time while the other agents act via their learned policies. This round-robin process collects realistic demonstrations and iteratively trains cooperative multi-agent behavior. Abstract-- Imitation Learning (IL) is a natural way for humans to teach robots, particularly when high-quality demonstrations are easy to obtain. While IL has been widely applied to single-robot settings, relatively few studies have addressed the extension of these methods to multi-agent systems, especially in settings where a single human must provide demonstrations to a team of collaborating robots. In this paper, we introduce and study Round-Robin Behavior Cloning (R2BC), a method that enables a single human operator to effectively train multi-robot systems through sequential, single-agent demonstrations. Our approach allows the human to teleoperate one agent at a time and incrementally teach multi-agent behavior to the entire system, without requiring demonstrations in the joint multi-agent action space.

Large Language Model agents excel at solving complex tasks through iterative reasoning and tool use, but typically depend on ultra-large, costly backbones. Existing distillation approaches train smaller students to imitate full teacher trajectories, yet reasoning and knowledge gaps between the teacher and student can cause compounding errors. We propose SCoRe, a student-centered framework in which the student generates training trajectories and the teacher corrects only the earliest error, producing training data matched to the student's ability and exposing specific weaknesses. The student is first fine-tuned on corrected trajectories. Subsequently, short-horizon reinforcement learning starts from the verified prefix preceding the earliest error, with target rewards assigned at that step. This design encourages autonomous problem-solving beyond imitation and enhances training stability. On 12 challenging benchmarks, a 7B-parameter student distilled with SCoRe matches the agentic performance of a 72B-parameter teacher. Recent advances in Large Language Models (LLMs) have led to the rise of "agents" (Xi et al., 2025). Unlike traditional single-pass generation, LLM agents solve complex problems through an iterative reasoning-action-observation loop, using frameworks such as ReAct (Y ao et al., 2023). Specifically, LLM agents decompose tasks into sub-goals (Reasoning), execute them via external tools such as code interpreters (Action) (Gao et al., 2023), and then refine their plans based on feedback from tool execution (Observation). By combining LLM planning with the precision of external tools, agents mitigate flaws of LLMs such as hallucinations, outdated knowledge, and weak numerical reasoning, achieving strong performance on real-world interactive tasks (Liu et al., 2023).

In recent years, extensive work has explored the application of the Transformer architecture to reinforcement learning problems. Among these, Decision Transformer (DT) (Chen et al., 2021) has gained particular attention in the context of offline reinforcement learning due to its ability to frame return-conditioned policy learning as a sequence modeling task. Most recently, Bhargava et al. (2024) provided a systematic comparison of DT with more conventional MLP-based offline RL algorithms, including Behavior Cloning (BC) and Conservative Q-Learning (CQL), and claimed DT exhibits superior performance in sparse-reward and low-quality data settings. In this paper, through experimentation on robotic manipulation tasks (Robomimic) and locomotion benchmarks (D4RL), we show that MLP-based Filtered Behavior Cloning (FBC) achieves competitive or superior performance compared to DT in sparse-reward environments. FBC simply filters out low-performing trajectories from the dataset and then performs ordinary behavior cloning on the filtered dataset. FBC is not only very straightforward, but it also requires less training data and is computationally more efficient. The results therefore suggest that DT is not preferable for sparse-reward environments. From prior work, arguably, DT is also not preferable for dense-reward environments. Thus, we pose the question: Is DT ever preferable?

-- Mixed Integer Linear Programs (MILPs) are essential tools for solving planning and scheduling problems across critical industries such as construction, manufacturing, and logistics. However, their widespread adoption is limited by long computational times, especially in large-scale, real-time scenarios. T o address this, we present a learning-based framework that leverages Behavior Cloning (BC) and Reinforcement Learning (RL) to train Graph Neural Networks (GNNs), producing high-quality initial solutions for warm-starting MILP solvers in Multi-Agent T ask Allocation and Scheduling Problems. Experimental results demonstrate that our method reduces optimization time and variance compared to traditional techniques while maintaining solution quality and feasibility. I. INTRODUCTION Mixed Integer Linear Programs (MILPs) serve as a fundamental framework for combinatorial optimization problems, facilitating solutions across a wide range of planning and scheduling tasks in logistics [1], construction [2] and manufacturing [3].

Decentralized Finance (DeFi) lending enables permission-less borrowing via smart contracts. However, it faces challenges in optimizing interest rates, mitigating bad debt, and improving capital efficiency. Rule-based interest-rate models struggle to adapt to dynamic market conditions, leading to inefficiencies. This work applies Offline Reinforcement Learning (RL) to optimize interest rate adjustments in DeFi lending protocols. Using historical data from Aave protocol, we evaluate three RL approaches: Conservative Q-Learning (CQL), Behavior Cloning (BC), and TD3 with Behavior Cloning (TD3-BC). TD3-BC demonstrates superior performance in balancing utilization, capital stability, and risk, outperforming existing models. It adapts effectively to historical stress events like the May 2021 crash and the March 2023 USDC depeg, showcasing potential for automated, real-time governance.

Imitation learning (IL) aims to mimic the behavior of an expert in a sequential decision making task by learning from demonstrations, and has been widely applied to robotics, autonomous driving, and autoregressive text generation. The simplest approach to IL, behavior cloning (BC) is thought to incur sample complexity with unfavorable quadratic dependence on the problem horizon, motivating a variety of different online algorithms that attain improved linear horizon dependence under stronger assumptions on the data and the learner's access to the expert. We revisit the apparent gap between offline and online IL from a learning-theoretic perspective, with a focus on general policy classes up to and including deep neural networks. Through a new analysis of BC with the logarithmic loss, we show that it is possible to achieve horizon-independent sample complexity in offline IL whenever (i) the range of the cumulative payoffs is controlled, and (ii) an appropriate notion of supervised learning complexity for the policy class is controlled. Specializing our results to deterministic, stationary policies, we show that the gap between offline and online IL is not fundamental: (i) it is possible to achieve linear dependence on horizon in offline IL under dense rewards (matching what was previously only known to be achievable in online IL); and (ii) without further assumptions on the policy class, online IL cannot improve over offline IL with the logarithmic loss, even in benign MDPs.

While internet-scale image and textual data have enabled strong generalization in Vision-Language Models (VLMs), the absence of internet-scale control data has impeded the development of similar generalization in standard reinforcement learning (RL) agents. Although VLMs are fundamentally limited in their ability to solve control tasks due to their lack of action-conditioned training data, their capacity for image understanding allows them to provide valuable feedback in RL tasks by recognizing successful outcomes. A key challenge in Reinforcement Learning from AI Feedback (RLAIF) is determining how best to integrate VLM-derived signals into the learning process. We explore this question in the context of offline RL and introduce a class of methods called sub-trajectory filtered optimization. We identify three key insights. First, trajectory length plays a crucial role in offline RL, as full-trajectory preference learning exacerbates the stitching problem, necessitating the use of sub-trajectories. Second, even in Markovian environments, a non-Markovian reward signal from a sequence of images is required to assess trajectory improvement, as VLMs do not interpret control actions and must rely on visual cues over time. Third, a simple yet effective approach--filtered and weighted behavior cloning--consistently outperforms more complex reinforcement learning from human feedback-based methods. We propose sub-trajectory filtered behavior cloning, a method that leverages VLM feedback on sub-trajectories while incorporating a retrospective filtering mechanism that removes sub-trajectories preceding failures to improve robustness and prevent turbulence. This study is preliminary; we provide initial evidence through evaluations on a toy control domain. Please enjoy our airport puns.

Behavior Cloning (BC) is a widely adopted visual imitation learning method in robot manipulation. Current BC approaches often enhance generalization by leveraging large datasets and incorporating additional visual and textual modalities to capture more diverse information. However, these methods overlook whether the learned representations contain redundant information and lack a solid theoretical foundation to guide the learning process. To address these limitations, we adopt an information-theoretic perspective and introduce mutual information to quantify and mitigate redundancy in latent representations. Building on this, we incorporate the Information Bottleneck (IB) principle into BC, which extends the idea of reducing redundancy by providing a structured framework for compressing irrelevant information while preserving task-relevant features. This work presents the first comprehensive study on redundancy in latent representations across various methods, backbones, and experimental settings, while extending the generalizability of the IB to BC. Extensive experiments and analyses on the CortexBench and LIBERO benchmarks demonstrate significant performance improvements with IB, underscoring the importance of reducing input data redundancy and highlighting its practical value for more practical applications. Project Page: https://baishuanghao.github.io/BC-IB.github.io.

Learning from Demonstration (LfD) algorithms have shown promising results in robotic manipulation tasks, but their vulnerability to adversarial attacks remains underexplored. This paper presents a comprehensive study of adversarial attacks on both classic and recently proposed algorithms, including Behavior Cloning (BC), LSTM-GMM, Implicit Behavior Cloning (IBC), Diffusion Policy (DP), and VQ-Behavior Transformer (VQ-BET). We study the vulnerability of these methods to untargeted, targeted and universal adversarial perturbations. While explicit policies, such as BC, LSTM-GMM and VQ-BET can be attacked in the same manner as standard computer vision models, we find that attacks for implicit and denoising policy models are nuanced and require developing novel attack methods. Our experiments on several simulated robotic manipulation tasks reveal that most of the current methods are highly vulnerable to adversarial perturbations. We also show that these attacks are transferable across algorithms, architectures, and tasks, raising concerning security vulnerabilities with potentially a white-box threat model. In addition, we test the efficacy of a randomized smoothing, a widely used adversarial defense technique, and highlight its limitation in defending against attacks on complex and multi-modal action distribution common in complex control tasks. In summary, our findings highlight the vulnerabilities of modern BC algorithms, paving way for future work in addressing such limitations.

In sequential decision-making environments, the primary approaches for training agents are Reinforcement Learning (RL) and Imitation Learning (IL). Unlike RL, which relies on modeling a reward function, IL leverages expert demonstrations, where an expert policy $\pi_e$ (e.g., a human) provides the desired behavior. Formally, a dataset $D$ of state-action pairs is provided: $D = {(s, a = \pi_e(s))}$. A common technique within IL is Behavior Cloning (BC), where a policy $\pi(s) = a$ is learned through supervised learning on $D$. Further improvements can be achieved by using an ensemble of $N$ individually trained BC policies, denoted as $E = {\pi_i(s)}{1 \leq i \leq N}$. The ensemble's action $a$ for a given state $s$ is the aggregated output of the $N$ actions: $a = \frac{1}{N} \sum{i} \pi_i(s)$. This paper addresses the issue of increasing action differences -- the observation that discrepancies between the $N$ predicted actions grow in states that are underrepresented in the training data. Large action differences can result in suboptimal aggregated actions. To address this, we propose a method that fosters greater alignment among the policies while preserving the diversity of their computations. This approach reduces action differences and ensures that the ensemble retains its inherent strengths, such as robustness and varied decision-making. We evaluate our approach across eight diverse environments, demonstrating a notable decrease in action differences and significant improvements in overall performance, as measured by mean episode returns.