Rohan Paleja

Aarav G Sane, Karthik Sivachandran, Rohan Paleja

Human coordination often relies on the ability to influence the beliefs of others through strategic action. In multi-agent reinforcement learning, opponent shaping attempts to replicate this influence, though existing methods typically operate within an opponent's parameter, policy, or value space. Meanwhile, belief-manipulation techniques in hidden-role games often rely on hard-coded objectives, such as deception or belief saturation. We propose Differentiable Belief-based Opponent Shaping (D-BOS), a first-order method that treats each observer's belief as the shaped opponent state and differentiates through $k$-step softmax-Bayes belief dynamics. Rather than explicitly rewarding deceptive or cooperative behavior, our method treats the belief state as the target for shaping. This allows the optimal strategy to emerge naturally from the environment's reward structure. This belief-space formulation provides an opponent-shaping signal by differentiating through opponent belief updates, and naturally extends to multiple observers by aggregating gradients over their individual inferred belief trajectories. Empirically, D-BOS outperforms PPO and BBM in hidden-role games, with the largest gains in mixed-motive settings.

Rohan Paleja, Muyleng Ghuy, Nadun Ranawaka Arachchige et al.

Recent advances in machine learning have led to growing interest in Explainable AI (xAI) to enable humans to gain insight into the decision-making of machine learning models. Despite this recent interest, the utility of xAI techniques has not yet been characterized in human-machine teaming. Importantly, xAI offers the promise of enhancing team situational awareness (SA) and shared mental model development, which are the key characteristics of effective human-machine teams. Rapidly developing such mental models is especially critical in ad hoc human-machine teaming, where agents do not have a priori knowledge of others' decision-making strategies. In this paper, we present two novel human-subject experiments quantifying the benefits of deploying xAI techniques within a human-machine teaming scenario. First, we show that xAI techniques can support SA ($p<0.05)$. Second, we examine how different SA levels induced via a collaborative AI policy abstraction affect ad hoc human-machine teaming performance. Importantly, we find that the benefits of xAI are not universal, as there is a strong dependence on the composition of the human-machine team. Novices benefit from xAI providing increased SA ($p<0.05$) but are susceptible to cognitive overhead ($p<0.05$). On the other hand, expert performance degrades with the addition of xAI-based support ($p<0.05$), indicating that the cost of paying attention to the xAI outweighs the benefits obtained from being provided additional information to enhance SA. Our results demonstrate that researchers must deliberately design and deploy the right xAI techniques in the right scenario by carefully considering human-machine team composition and how the xAI method augments SA.

Letian Chen, Sravan Jayanthi, Rohan Paleja et al.

Learning from Demonstration (LfD) approaches empower end-users to teach robots novel tasks via demonstrations of the desired behaviors, democratizing access to robotics. However, current LfD frameworks are not capable of fast adaptation to heterogeneous human demonstrations nor the large-scale deployment in ubiquitous robotics applications. In this paper, we propose a novel LfD framework, Fast Lifelong Adaptive Inverse Reinforcement learning (FLAIR). Our approach (1) leverages learned strategies to construct policy mixtures for fast adaptation to new demonstrations, allowing for quick end-user personalization, (2) distills common knowledge across demonstrations, achieving accurate task inference; and (3) expands its model only when needed in lifelong deployments, maintaining a concise set of prototypical strategies that can approximate all behaviors via policy mixtures. We empirically validate that FLAIR achieves adaptability (i.e., the robot adapts to heterogeneous, user-specific task preferences), efficiency (i.e., the robot achieves sample-efficient adaptation), and scalability (i.e., the model grows sublinearly with the number of demonstrations while maintaining high performance). FLAIR surpasses benchmarks across three control tasks with an average 57% improvement in policy returns and an average 78% fewer episodes required for demonstration modeling using policy mixtures. Finally, we demonstrate the success of FLAIR in a table tennis task and find users rate FLAIR as having higher task (p<.05) and personalization (p<.05) performance.

Sean Ye, Manisha Natarajan, Zixuan Wu et al.

The need for opponent modeling and tracking arises in several real-world scenarios, such as professional sports, video game design, and drug-trafficking interdiction. In this work, we present Graph based Adversarial Modeling with Mutal Information (GrAMMI) for modeling the behavior of an adversarial opponent agent. GrAMMI is a novel graph neural network (GNN) based approach that uses mutual information maximization as an auxiliary objective to predict the current and future states of an adversarial opponent with partial observability. To evaluate GrAMMI, we design two large-scale, pursuit-evasion domains inspired by real-world scenarios, where a team of heterogeneous agents is tasked with tracking and interdicting a single adversarial agent, and the adversarial agent must evade detection while achieving its own objectives. With the mutual information formulation, GrAMMI outperforms all baselines in both domains and achieves 31.68% higher log-likelihood on average for future adversarial state predictions across both domains.

Xinchen Jin, Aditya Chatterjee, Pranav Kumar et al.

Vision-Language-Action (VLA) policies translate language and visual inputs into robot actions, where their hidden representations directly shape closed-loop behavior. However, mechanistic interpretability tools from language and vision-language models do not transfer cleanly to VLAs: outputs are robot actions rather than human-readable tokens, and interventions can only be tested via expensive closed-loop rollouts. We propose an event-grounded interpretability pipeline that anchors SAE feature analysis to behavioral events rather than text contexts. End-effector keyframes are clustered within each task using visual, state, and temporal cues, linking SAE features to behaviorally salient events and, via optional VLM annotations, to semantic context. To our knowledge, our pipeline is among the first to ground SAE-based VLA analysis in closed-loop behavioral events. Across two simulation architectures and a real-robot study, event-grounded ranking yields the strongest causal effects on OpenVLA and transfers to the continuous action chunks of $π_{0.5}$. SAE is a sparse but imperfect intervention basis: usability varies with architecture and intervention site, and aggressive intervention reveals safety and interpretability limits. Overall, event-grounded SAE analysis emerges as a practical starting point for behavior-anchored VLA interpretability, motivating future work on SAE features beyond action-aligned coordinates, finer-grained closed-loop evaluation, and safe interventions for high-stakes VLA deployments. Code is available at \url{https://github.com/xc-j/Event-SAE}.

Zixuan Wu, Sean Ye, Manisha Natarajan et al.

We study a search and tracking (S&T) problem where a team of dynamic search agents must collaborate to track an adversarial, evasive agent. The heterogeneous search team may only have access to a limited number of past adversary trajectories within a large search space. This problem is challenging for both model-based searching and reinforcement learning (RL) methods since the adversary exhibits reactionary and deceptive evasive behaviors in a large space leading to sparse detections for the search agents. To address this challenge, we propose a novel Multi-Agent RL (MARL) framework that leverages the estimated adversary location from our learnable filtering model. We show that our MARL architecture can outperform all baselines and achieves a 46% increase in detection rate.

Wei Sheng, Rohan Paleja

While AI agents are rapidly advancing from isolated tools to interactive collaborators, data-driven human-machine teaming (HMT) methods remain costly in their reliance on human interaction data across domains, teammates, and team sizes. Zero-shot coordination (ZSC) addresses this bottleneck by simulating diverse partner populations to approximate how unseen partners might behave. However, partner coverage alone is insufficient as team settings scale and communication becomes degraded. To remedy this deficiency, we propose Influence-Based Team Steering (IBTS), a framework that uses influence shaping to incentivize agents to discover diverse, high-performing team interaction patterns and further steers ongoing trajectories toward stronger learned coordination modes. We assess IBTS on Overcooked-AI in both two-agent and three-agent settings, allowing us to test whether learned coordination structure transfers beyond dyadic interaction. Our evaluation includes simulated partners, synthetic partner-style variation, and, to our knowledge, the first 30-subject Overcooked-AI HMT study involving two real human teammates and one machine teammate. Across these evaluations, IBTS improves team performance against competing baselines, highlighting the need for scaled ZSC to combine sparse-reward coordination mechanisms with partner-variation coverage rather than relying on diversity alone.

Edward Gu, Ho Chit Siu, Melanie Platt et al.

In this work, we present two novel contributions toward improving research in human-machine teaming (HMT): 1) a Minecraft testbed to accelerate testing and deployment of collaborative AI agents and 2) a tool to allow users to revisit and analyze behaviors within an HMT episode to facilitate shared mental model development. Our browser-based Minecraft testbed allows for rapid testing of collaborative agents in a continuous-space, real-time, partially-observable environment with real humans without cumbersome setup typical to human-AI interaction user studies. As Minecraft has an extensive player base and a rich ecosystem of pre-built AI agents, we hope this contribution can help to facilitate research quickly in the design of new collaborative agents and in understanding different human factors within HMT. Our mental model alignment tool facilitates user-led post-mission analysis by including video displays of first-person perspectives of the team members (i.e., the human and AI) that can be replayed, and a chat interface that leverages GPT-4 to provide answers to various queries regarding the AI's experiences and model details.

Zhaoxin Li, Zhang Xi-Jia, Batuhan Altundas et al.

Semantic interpretability in Reinforcement Learning (RL) enables transparency and verifiability of decision-making. Achieving semantic interpretability in reinforcement learning requires (1) a feature space composed of human-understandable concepts and (2) a policy that is interpretable and verifiable. However, constructing such a feature space has traditionally relied on manual human specification, which often fails to generalize to unseen environments. Moreover, even when interpretable features are available, most reinforcement learning algorithms employ black-box models as policies, thereby hindering transparency. We introduce interpretable Tree-based Reinforcement learning via Automated Concept Extraction (iTRACE), an automated framework that leverages pre-trained vision-language models (VLM) for semantic feature extraction and train a interpretable tree-based model via RL. To address the impracticality of running VLMs in RL loops, we distill their outputs into a lightweight model. By leveraging Vision-Language Models (VLMs) to automate tree-based reinforcement learning, iTRACE loosens the reliance the need for human annotation that is traditionally required by interpretable models. In addition, it addresses key limitations of VLMs alone, such as their lack of grounding in action spaces and their inability to directly optimize policies. We evaluate iTRACE across three domains: Atari games, grid-world navigation, and driving. The results show that iTRACE outperforms other interpretable policy baselines and matches the performance of black-box policies on the same interpretable feature space.

Manasi Sharma, Ho Chit Siu, Rohan Paleja et al.

The emergence of Large Language Models (LLMs) has revealed a growing need for human-AI collaboration, especially in creative decision-making scenarios where trust and reliance are paramount. Through human studies and model evaluations on the open-ended News Headline Generation task from the LaMP benchmark, we analyze how the framing and presence of explanations affect user trust and model performance. Overall, we provide evidence that adding an explanation in the model response to justify its reasoning significantly increases self-reported user trust in the model when the user has the opportunity to compare various responses. Position and faithfulness of these explanations are also important factors. However, these gains disappear when users are shown responses independently, suggesting that humans trust all model responses, including deceptive ones, equitably when they are shown in isolation. Our findings urge future research to delve deeper into the nuanced evaluation of trust in human-machine teaming systems.

Rohan Paleja, Yaru Niu, Andrew Silva et al.

Gradient-based approaches in reinforcement learning (RL) have achieved tremendous success in learning policies for autonomous vehicles. While the performance of these approaches warrants real-world adoption, these policies lack interpretability, limiting deployability in the safety-critical and legally-regulated domain of autonomous driving (AD). AD requires interpretable and verifiable control policies that maintain high performance. We propose Interpretable Continuous Control Trees (ICCTs), a tree-based model that can be optimized via modern, gradient-based, RL approaches to produce high-performing, interpretable policies. The key to our approach is a procedure for allowing direct optimization in a sparse decision-tree-like representation. We validate ICCTs against baselines across six domains, showing that ICCTs are capable of learning interpretable policy representations that parity or outperform baselines by up to 33% in AD scenarios while achieving a 300x-600x reduction in the number of policy parameters against deep learning baselines. Furthermore, we demonstrate the interpretability and utility of our ICCTs through a 14-car physical robot demonstration.

Letian Chen, Rohan Paleja, Matthew Gombolay

Learning from Demonstration (LfD) seeks to democratize robotics by enabling non-roboticist end-users to teach robots to perform novel tasks by providing demonstrations. However, as demonstrators are typically non-experts, modern LfD techniques are unable to produce policies much better than the suboptimal demonstration. A previously-proposed framework, SSRR, has shown success in learning from suboptimal demonstration but relies on noise-injected trajectories to infer an idealized reward function. A random approach such as noise-injection to generate trajectories has two key drawbacks: 1) Performance degradation could be random depending on whether the noise is applied to vital states and 2) Noise-injection generated trajectories may have limited suboptimality and therefore will not accurately represent the whole scope of suboptimality. We present Systematic Self-Supervised Reward Regression, S3RR, to investigate systematic alternatives for trajectory degradation. We carry out empirical evaluations and find S3RR can learn comparable or better reward correlation with ground-truth against a state-of-the-art learning from suboptimal demonstration framework.

Letian Chen, Rohan Paleja, Matthew Gombolay

Learning from Demonstration (LfD) seeks to democratize robotics by enabling non-roboticist end-users to teach robots to perform a task by providing a human demonstration. However, modern LfD techniques, e.g. inverse reinforcement learning (IRL), assume users provide at least stochastically optimal demonstrations. This assumption fails to hold in most real-world scenarios. Recent attempts to learn from sub-optimal demonstration leverage pairwise rankings and following the Luce-Shepard rule. However, we show these approaches make incorrect assumptions and thus suffer from brittle, degraded performance. We overcome these limitations in developing a novel approach that bootstraps off suboptimal demonstrations to synthesize optimality-parameterized data to train an idealized reward function. We empirically validate we learn an idealized reward function with ~0.95 correlation with ground-truth reward versus ~0.75 for prior work. We can then train policies achieving ~200% improvement over the suboptimal demonstration and ~90% improvement over prior work. We present a physical demonstration of teaching a robot a topspin strike in table tennis that achieves 32% faster returns and 40% more topspin than user demonstration.

Rohan Paleja, Matthew Gombolay

The development of human-robot systems able to leverage the strengths of both humans and their robotic counterparts has been greatly sought after because of the foreseen, broad-ranging impact across industry and research. We believe the true potential of these systems cannot be reached unless the robot is able to act with a high level of autonomy, reducing the burden of manual tasking or teleoperation. To achieve this level of autonomy, robots must be able to work fluidly with its human partners, inferring their needs without explicit commands. This inference requires the robot to be able to detect and classify the heterogeneity of its partners. We propose a framework for learning from heterogeneous demonstration based upon Bayesian inference and evaluate a suite of approaches on a real-world dataset of gameplay from StarCraft II. This evaluation provides evidence that our Bayesian approach can outperform conventional methods by up to 12.8$%$.

Letian Chen, Rohan Paleja, Muyleng Ghuy et al.

Reinforcement learning (RL) has achieved tremendous success as a general framework for learning how to make decisions. However, this success relies on the interactive hand-tuning of a reward function by RL experts. On the other hand, inverse reinforcement learning (IRL) seeks to learn a reward function from readily-obtained human demonstrations. Yet, IRL suffers from two major limitations: 1) reward ambiguity - there are an infinite number of possible reward functions that could explain an expert's demonstration and 2) heterogeneity - human experts adopt varying strategies and preferences, which makes learning from multiple demonstrators difficult due to the common assumption that demonstrators seeks to maximize the same reward. In this work, we propose a method to jointly infer a task goal and humans' strategic preferences via network distillation. This approach enables us to distill a robust task reward (addressing reward ambiguity) and to model each strategy's objective (handling heterogeneity). We demonstrate our algorithm can better recover task reward and strategy rewards and imitate the strategies in two simulated tasks and a real-world table tennis task.

Rohan Paleja, Andrew Silva, Letian Chen et al.

Resource scheduling and coordination is an NP-hard optimization requiring an efficient allocation of agents to a set of tasks with upper- and lower bound temporal and resource constraints. Due to the large-scale and dynamic nature of resource coordination in hospitals and factories, human domain experts manually plan and adjust schedules on the fly. To perform this job, domain experts leverage heterogeneous strategies and rules-of-thumb honed over years of apprenticeship. What is critically needed is the ability to extract this domain knowledge in a heterogeneous and interpretable apprenticeship learning framework to scale beyond the power of a single human expert, a necessity in safety-critical domains. We propose a personalized and interpretable apprenticeship scheduling algorithm that infers an interpretable representation of all human task demonstrators by extracting decision-making criteria via an inferred, personalized embedding non-parametric in the number of demonstrator types. We achieve near-perfect LfD accuracy in synthetic domains and 88.22\% accuracy on a planning domain with real-world, outperforming baselines. Finally, our user study showed our methodology produces more interpretable and easier-to-use models than neural networks ($p < 0.05$).

Rohan Paleja, Matthew Gombolay

For assistive robots and virtual agents to achieve ubiquity, machines will need to anticipate the needs of their human counterparts. The field of Learning from Demonstration (LfD) has sought to enable machines to infer predictive models of human behavior for autonomous robot control. However, humans exhibit heterogeneity in decision-making, which traditional LfD approaches fail to capture. To overcome this challenge, we propose a Bayesian LfD framework to infer an integrated representation of all human task demonstrators by inferring human-specific embeddings, thereby distilling their unique characteristics. We validate our approach is able to outperform state-of-the-art techniques on both synthetic and real-world data sets.