Embarrassingly Parallel GFlowNets

GFlowNets are a promising alternative to MCMC sampling for discrete compositional random variables. Training GFlowNets requires repeated evaluations of the unnormalized target distribution or reward function. However, for large-scale posterior sampling, this may be prohibitive since it incurs traversing the data several times. Moreover, if the data are distributed across clients, employing standard GFlowNets leads to intensive client-server communication. To alleviate both these issues, we propose embarrassingly parallel GFlowNet (EP-GFlowNet). EP-GFlowNet is a provably correct divide-and-conquer method to sample from product distributions of the form $R(\cdot) \propto R_1(\cdot) ... R_N(\cdot)$ -- e.g., in parallel or federated Bayes, where each $R_n$ is a local posterior defined on a data partition. First, in parallel, we train a local GFlowNet targeting each $R_n$ and send the resulting models to the server. Then, the server learns a global GFlowNet by enforcing our newly proposed \emph{aggregating balance} condition, requiring a single communication step. Importantly, EP-GFlowNets can also be applied to multi-objective optimization and model reuse. Our experiments illustrate the EP-GFlowNets's effectiveness on many tasks, including parallel Bayesian phylogenetics, multi-objective multiset, sequence generation, and federated Bayesian structure learning.

Video-Language Critic: Transferable Reward Functions for Language-Conditioned Robotics

Natural language is often the easiest and most convenient modality for humans to specify tasks for robots. However, learning to ground language to behavior typically requires impractical amounts of diverse, language-annotated demonstrations collected on each target robot. In this work, we aim to separate the problem of what to accomplish from how to accomplish it, as the former can benefit from substantial amounts of external observation-only data, and only the latter depends on a specific robot embodiment. To this end, we propose Video-Language Critic, a reward model that can be trained on readily available cross-embodiment data using contrastive learning and a temporal ranking objective, and use it to score behavior traces from a separate reinforcement learning actor. When trained on Open X-Embodiment data, our reward model enables 2x more sample-efficient policy training on Meta-World tasks than a sparse reward only, despite a significant domain gap. Using in-domain data but in a challenging task generalization setting on Meta-World, we further demonstrate more sample-efficient training than is possible with prior language-conditioned reward models that are either trained with binary classification, use static images, or do not leverage the temporal information present in video data.

Attaining Human`s Desirable Outcomes in Human-AI Interaction via Structural Causal Games

In human-AI interaction, a prominent goal is to attain human`s desirable outcome with the assistance of AI agents, which can be ideally delineated as a problem of seeking the optimal Nash Equilibrium that matches the human`s desirable outcome. However, reaching the outcome is usually challenging due to the existence of multiple Nash Equilibria that are related to the assisting task but do not correspond to the human`s desirable outcome. To tackle this issue, we employ a theoretical framework called structural causal game (SCG) to formalize the human-AI interactive process. Furthermore, we introduce a strategy referred to as pre-policy intervention on the SCG to steer AI agents towards attaining the human`s desirable outcome. In more detail, a pre-policy is learned as a generalized intervention to guide the agents` policy selection, under a transparent and interpretable procedure determined by the SCG. To make the framework practical, we propose a reinforcement learning-like algorithm to search out this pre-policy. The proposed algorithm is tested in both gridworld environments and realistic dialogue scenarios with large language models, demonstrating its adaptability in a broader class of problems and potential effectiveness in real-world situations.

Heteroscedastic Preferential Bayesian Optimization with Informative Noise Distributions

Preferential Bayesian optimization (PBO) is a sample-efficient framework for learning human preferences between candidate designs. PBO classically relies on homoscedastic noise models to represent human aleatoric uncertainty. Yet, such noise fails to accurately capture the varying levels of human aleatoric uncertainty, particularly when the user possesses partial knowledge among different pairs of candidates. For instance, a chemist with solid expertise in glucose-related molecules may easily compare two compounds from that family while struggling to compare alcohol-related molecules. Currently, PBO overlooks this uncertainty during the search for a new candidate through the maximization of the acquisition function, consequently underestimating the risk associated with human uncertainty. To address this issue, we propose a heteroscedastic noise model to capture human aleatoric uncertainty. This model adaptively assigns noise levels based on the distance of a specific input to a predefined set of reliable inputs known as anchors provided by the human. Anchors encapsulate partial knowledge and offer insight into the comparative difficulty of evaluating different candidate pairs. Such a model can be seamlessly integrated into the acquisition function, thus leading to candidate design pairs that elegantly trade informativeness and ease of comparison for the human expert. We perform an extensive empirical evaluation of the proposed approach, demonstrating a consistent improvement over homoscedastic PBO.

In-n-Out: Calibrating Graph Neural Networks for Link Prediction

Deep neural networks are notoriously miscalibrated, i.e., their outputs do not reflect the true probability of the event we aim to predict. While networks for tabular or image data are usually overconfident, recent works have shown that graph neural networks (GNNs) show the opposite behavior for node-level classification. But what happens when we are predicting links? We show that, in this case, GNNs often exhibit a mixed behavior. More specifically, they may be overconfident in negative predictions while being underconfident in positive ones. Based on this observation, we propose IN-N-OUT, the first-ever method to calibrate GNNs for link prediction. IN-N-OUT is based on two simple intuitions: i) attributing true/false labels to an edge while respecting a GNNs prediction should cause but small fluctuations in that edge's embedding; and, conversely, ii) if we label that same edge contradicting our GNN, embeddings should change more substantially. An extensive experimental campaign shows that IN-N-OUT significantly improves the calibration of GNNs in link prediction, consistently outperforming the baselines available -- which are not designed for this specific task.

Cooperative Bayesian Optimization for Imperfect Agents

We introduce a cooperative Bayesian optimization problem for optimizing black-box functions of two variables where two agents choose together at which points to query the function but have only control over one variable each. This setting is inspired by human-AI teamwork, where an AI-assistant helps its human user solve a problem, in this simplest case, collaborative optimization. We formulate the solution as sequential decision-making, where the agent we control models the user as a computationally rational agent with prior knowledge about the function. We show that strategic planning of the queries enables better identification of the global maximum of the function as long as the user avoids excessive exploration. This planning is made possible by using Bayes Adaptive Monte Carlo planning and by endowing the agent with a user model that accounts for conservative belief updates and exploratory sampling of the points to query.

Online Learning of Human Constraints from Feedback in Shared Autonomy

Real-time collaboration with humans poses challenges due to the different behavior patterns of humans resulting from diverse physical constraints. Existing works typically focus on learning safety constraints for collaboration, or how to divide and distribute the subtasks between the participating agents to carry out the main task. In contrast, we propose to learn a human constraints model that, in addition, considers the diverse behaviors of different human operators. We consider a type of collaboration in a shared-autonomy fashion, where both a human operator and an assistive robot act simultaneously in the same task space that affects each other's actions. The task of the assistive agent is to augment the skill of humans to perform a shared task by supporting humans as much as possible, both in terms of reducing the workload and minimizing the discomfort for the human operator. Therefore, we propose an augmentative assistant agent capable of learning and adapting to human physical constraints, aligning its actions with the ergonomic preferences and limitations of the human operator.

Open Ad Hoc Teamwork with Cooperative Game Theory

Ad hoc teamwork poses a challenging problem, requiring the design of an agent to collaborate with teammates without prior coordination or joint training. Open ad hoc teamwork further complicates this challenge by considering environments with a changing number of teammates, referred to as open teams. The state-of-the-art solution to this problem is graph-based policy learning (GPL), leveraging the generalizability of graph neural networks to handle an unrestricted number of agents and effectively address open teams. GPL's performance is superior to other methods, but its joint Q-value representation presents challenges for interpretation, hindering further development of this research line and applicability. In this paper, we establish a new theory to give an interpretation for the joint Q-value representation employed in GPL, from the perspective of cooperative game theory. Building on our theory, we propose a novel algorithm based on GPL framework, to complement the critical features that facilitate learning, but overlooked in GPL. Through experiments, we demonstrate the correctness of our theory by comparing the performance of the resulting algorithm with GPL in dynamic team compositions.

Estimating treatment effects from single-arm trials via latent-variable modeling

Randomized controlled trials (RCTs) are the accepted standard for treatment effect estimation but they can be infeasible due to ethical reasons and prohibitive costs. Single-arm trials, where all patients belong to the treatment group, can be a viable alternative but require access to an external control group. We propose an identifiable deep latent-variable model for this scenario that can also account for missing covariate observations by modeling their structured missingness patterns. Our method uses amortized variational inference to learn both group-specific and identifiable shared latent representations, which can subsequently be used for (i) patient matching if treatment outcomes are not available for the treatment group, or for (ii) direct treatment effect estimation assuming outcomes are available for both groups. We evaluate the model on a public benchmark as well as on a data set consisting of a published RCT study and real-world electronic health records. Compared to previous methods, our results show improved performance both for direct treatment effect estimation as well as for effect estimation via patient matching.

The Fundamental Dilemma of Bayesian Active Meta-learning

Many applications involve estimation of parameters that generalize across multiple diverse, but related, data-scarce task environments. Bayesian active meta-learning, a form of sequential optimal experimental design, provides a framework for solving such problems. The active meta-learner's goal is to gain transferable knowledge (estimate the transferable parameters) in the presence of idiosyncratic characteristics of the current task (task-specific parameters). We show that in such a setting, greedy pursuit of this goal can actually hurt estimation of the transferable parameters (induce so-called negative transfer). The learner faces a dilemma akin to but distinct from the exploration--exploitation dilemma: should they spend their acquisition budget pursuing transferable knowledge, or identifying the current task-specific parameters? We show theoretically that some tasks pose an inevitable and arbitrarily large threat of negative transfer, and that task identification is critical to reducing this threat. Our results generalize to analysis of prior misspecification over nuisance parameters. Finally, we empirically illustrate circumstances that lead to negative transfer.