arXiv subjects

Yitao Liang

Publications and source records attributed to Yitao Liang.

69 records · Page 4Linked to original sources

arXiv2023

SQA3D: Situated Question Answering in 3D Scenes

We propose a new task to benchmark scene understanding of embodied agents: Situated Question Answering in 3D Scenes (SQA3D). Given a scene context (e.g., 3D scan), SQA3D requires the tested agent to first understand its situation (position, orientation, etc.) in the 3D scene as described by text, then reason about its surrounding environment and answer a question under that situation. Based upon 650 scenes from ScanNet, we provide a dataset centered around 6.8k unique situations, along with 20.4k descriptions and 33.4k diverse reasoning questions for these situations. These questions examine a wide spectrum of reasoning capabilities for an intelligent agent, ranging from spatial relation comprehension to commonsense understanding, navigation, and multi-hop reasoning. SQA3D imposes a significant challenge to current multi-modal especially 3D reasoning models. We evaluate various state-of-the-art approaches and find that the best one only achieves an overall score of 47.20%, while amateur human participants can reach 90.06%. We believe SQA3D could facilitate future embodied AI research with stronger situation understanding and reasoning capability.

cs.CV↗

arXiv2023

Understanding the Distillation Process from Deep Generative Models to Tractable Probabilistic Circuits

Probabilistic Circuits (PCs) are a general and unified computational framework for tractable probabilistic models that support efficient computation of various inference tasks (e.g., computing marginal probabilities). Towards enabling such reasoning capabilities in complex real-world tasks, Liu et al. (2022) propose to distill knowledge (through latent variable assignments) from less tractable but more expressive deep generative models. However, it is still unclear what factors make this distillation work well. In this paper, we theoretically and empirically discover that the performance of a PC can exceed that of its teacher model. Therefore, instead of performing distillation from the most expressive deep generative model, we study what properties the teacher model and the PC should have in order to achieve good distillation performance. This leads to a generic algorithmic improvement as well as other data-type-specific ones over the existing latent variable distillation pipeline. Empirically, we outperform SoTA TPMs by a large margin on challenging image modeling benchmarks. In particular, on ImageNet32, PCs achieve 4.06 bits-per-dimension, which is only 0.34 behind variational diffusion models (Kingma et al., 2021).

cs.LG↗

arXiv2022

Efficient Meta Reinforcement Learning for Preference-based Fast Adaptation

Learning new task-specific skills from a few trials is a fundamental challenge for artificial intelligence. Meta reinforcement learning (meta-RL) tackles this problem by learning transferable policies that support few-shot adaptation to unseen tasks. Despite recent advances in meta-RL, most existing methods require the access to the environmental reward function of new tasks to infer the task objective, which is not realistic in many practical applications. To bridge this gap, we study the problem of few-shot adaptation in the context of human-in-the-loop reinforcement learning. We develop a meta-RL algorithm that enables fast policy adaptation with preference-based feedback. The agent can adapt to new tasks by querying human's preference between behavior trajectories instead of using per-step numeric rewards. By extending techniques from information theory, our approach can design query sequences to maximize the information gain from human interactions while tolerating the inherent error of non-expert human oracle. In experiments, we extensively evaluate our method, Adaptation with Noisy OracLE (ANOLE), on a variety of meta-RL benchmark tasks and demonstrate substantial improvement over baseline algorithms in terms of both feedback efficiency and error tolerance.

cs.LG↗

arXiv2021

Towards an Interpretable Latent Space in Structured Models for Video Prediction

We focus on the task of future frame prediction in video governed by underlying physical dynamics. We work with models which are object-centric, i.e., explicitly work with object representations, and propagate a loss in the latent space. Specifically, our research builds on recent work by Kipf et al. \cite{kipf&al20}, which predicts the next state via contrastive learning of object interactions in a latent space using a Graph Neural Network. We argue that injecting explicit inductive bias in the model, in form of general physical laws, can help not only make the model more interpretable, but also improve the overall prediction of model. As a natural by-product, our model can learn feature maps which closely resemble actual object positions in the image, without having any explicit supervision about the object positions at the training time. In comparison with earlier works \cite{jaques&al20}, which assume a complete knowledge of the dynamics governing the motion in the form of a physics engine, we rely only on the knowledge of general physical laws, such as, world consists of objects, which have position and velocity. We propose an additional decoder based loss in the pixel space, imposed in a curriculum manner, to further refine the latent space predictions. Experiments in multiple different settings demonstrate that while Kipf et al. model is effective at capturing object interactions, our model can be significantly more effective at localising objects, resulting in improved performance in 3 out of 4 domains that we experiment with. Additionally, our model can learn highly intrepretable feature maps, resembling actual object positions.

cs.LG↗

arXiv2020

SAM: Squeeze-and-Mimic Networks for Conditional Visual Driving Policy Learning

We describe a policy learning approach to map visual inputs to driving controls conditioned on turning command that leverages side tasks on semantics and object affordances via a learned representation trained for driving. To learn this representation, we train a squeeze network to drive using annotations for the side task as input. This representation encodes the driving-relevant information associated with the side task while ideally throwing out side task-relevant but driving-irrelevant nuisances. We then train a mimic network to drive using only images as input and use the squeeze network's latent representation to supervise the mimic network via a mimicking loss. Notably, we do not aim to achieve the side task nor to learn features for it; instead, we aim to learn, via the mimicking loss, a representation of the side task annotations directly useful for driving. We test our approach using the CARLA simulator. In addition, we introduce a more challenging but realistic evaluation protocol that considers a run that reaches the destination successful only if it does not violate common traffic rules. A video summarizing this work is available at https://youtu.be/ipKAMzmJpMs , and code is available at https://github.com/twsq/sam-driving .

cs.CV↗

arXiv2020

On Effective Parallelization of Monte Carlo Tree Search

Despite its groundbreaking success in Go and computer games, Monte Carlo Tree Search (MCTS) is computationally expensive as it requires a substantial number of rollouts to construct the search tree, which calls for effective parallelization. However, how to design effective parallel MCTS algorithms has not been systematically studied and remains poorly understood. In this paper, we seek to lay its first theoretical foundation, by examining the potential performance loss caused by parallelization when achieving a desired speedup. In particular, we discover the necessary conditions of achieving a desirable parallelization performance, and highlight two of their practical benefits. First, by examining whether existing parallel MCTS algorithms satisfy these conditions, we identify key design principles that should be inherited by future algorithms, for example tracking the unobserved samples (used in WU-UCT (Liu et al., 2020)). We theoretically establish this essential design facilitates $\mathcal{O} ( \ln n + M / \sqrt{\ln n} )$ cumulative regret when the maximum tree depth is 2, where $n$ is the number of rollouts and $M$ is the number of workers. A regret of this form is highly desirable, as compared to $\mathcal{O} ( \ln n )$ regret incurred by a sequential counterpart, its excess part approaches zero as $n$ increases. Second, and more importantly, we demonstrate how the proposed necessary conditions can be adopted to design more effective parallel MCTS algorithms. To illustrate this, we propose a new parallel MCTS algorithm, called BU-UCT, by following our theoretical guidelines. The newly proposed algorithm, albeit preliminary, out-performs four competitive baselines on 11 out of 15 Atari games. We hope our theoretical results could inspire future work of more effective parallel MCTS.

cs.LG↗

arXiv2020

Handling Missing Data in Decision Trees: A Probabilistic Approach

Decision trees are a popular family of models due to their attractive properties such as interpretability and ability to handle heterogeneous data. Concurrently, missing data is a prevalent occurrence that hinders performance of machine learning models. As such, handling missing data in decision trees is a well studied problem. In this paper, we tackle this problem by taking a probabilistic approach. At deployment time, we use tractable density estimators to compute the "expected prediction" of our models. At learning time, we fine-tune parameters of already learned trees by minimizing their "expected prediction loss" w.r.t.\ our density estimators. We provide brief experiments showcasing effectiveness of our methods compared to few baselines.

cs.LG↗

arXiv2020

Off-Policy Deep Reinforcement Learning with Analogous Disentangled Exploration

Off-policy reinforcement learning (RL) is concerned with learning a rewarding policy by executing another policy that gathers samples of experience. While the former policy (i.e. target policy) is rewarding but in-expressive (in most cases, deterministic), doing well in the latter task, in contrast, requires an expressive policy (i.e. behavior policy) that offers guided and effective exploration. Contrary to most methods that make a trade-off between optimality and expressiveness, disentangled frameworks explicitly decouple the two objectives, which each is dealt with by a distinct separate policy. Although being able to freely design and optimize the two policies with respect to their own objectives, naively disentangling them can lead to inefficient learning or stability issues. To mitigate this problem, our proposed method Analogous Disentangled Actor-Critic (ADAC) designs analogous pairs of actors and critics. Specifically, ADAC leverages a key property about Stein variational gradient descent (SVGD) to constraint the expressive energy-based behavior policy with respect to the target one for effective exploration. Additionally, an analogous critic pair is introduced to incorporate intrinsic rewards in a principled manner, with theoretical guarantees on the overall learning stability and effectiveness. We empirically evaluate environment-reward-only ADAC on 14 continuous-control tasks and report the state-of-the-art on 10 of them. We further demonstrate ADAC, when paired with intrinsic rewards, outperform alternatives in exploration-challenging tasks.

cs.LG↗

arXiv2019

On Tractable Computation of Expected Predictions

Computing expected predictions of discriminative models is a fundamental task in machine learning that appears in many interesting applications such as fairness, handling missing values, and data analysis. Unfortunately, computing expectations of a discriminative model with respect to a probability distribution defined by an arbitrary generative model has been proven to be hard in general. In fact, the task is intractable even for simple models such as logistic regression and a naive Bayes distribution. In this paper, we identify a pair of generative and discriminative models that enables tractable computation of expectations, as well as moments of any order, of the latter with respect to the former in case of regression. Specifically, we consider expressive probabilistic circuits with certain structural constraints that support tractable probabilistic inference. Moreover, we exploit the tractable computation of high-order moments to derive an algorithm to approximate the expectations for classification scenarios in which exact computations are intractable. Our framework to compute expected predictions allows for handling of missing data during prediction time in a principled and accurate way and enables reasoning about the behavior of discriminative models. We empirically show our algorithm to consistently outperform standard imputation techniques on a variety of datasets. Finally, we illustrate how our framework can be used for exploratory data analysis.

cs.LG↗

arXiv2019

Horizon: Facebook's Open Source Applied Reinforcement Learning Platform

In this paper we present Horizon, Facebook's open source applied reinforcement learning (RL) platform. Horizon is an end-to-end platform designed to solve industry applied RL problems where datasets are large (millions to billions of observations), the feedback loop is slow (vs. a simulator), and experiments must be done with care because they don't run in a simulator. Unlike other RL platforms, which are often designed for fast prototyping and experimentation, Horizon is designed with production use cases as top of mind. The platform contains workflows to train popular deep RL algorithms and includes data preprocessing, feature transformation, distributed training, counterfactual policy evaluation, optimized serving, and a model-based data understanding tool. We also showcase and describe real examples where reinforcement learning models trained with Horizon significantly outperformed and replaced supervised learning systems at Facebook.

cs.LG↗

arXiv2019

What to Expect of Classifiers? Reasoning about Logistic Regression with Missing Features

While discriminative classifiers often yield strong predictive performance, missing feature values at prediction time can still be a challenge. Classifiers may not behave as expected under certain ways of substituting the missing values, since they inherently make assumptions about the data distribution they were trained on. In this paper, we propose a novel framework that classifies examples with missing features by computing the expected prediction with respect to a feature distribution. Moreover, we use geometric programming to learn a naive Bayes distribution that embeds a given logistic regression classifier and can efficiently take its expected predictions. Empirical evaluations show that our model achieves the same performance as the logistic regression with all features observed, and outperforms standard imputation techniques when features go missing during prediction time. Furthermore, we demonstrate that our method can be used to generate "sufficient explanations" of logistic regression classifications, by removing features that do not affect the classification.

cs.LG↗

arXiv2019

Learning Logistic Circuits

This paper proposes a new classification model called logistic circuits. On MNIST and Fashion datasets, our learning algorithm outperforms neural networks that have an order of magnitude more parameters. Yet, logistic circuits have a distinct origin in symbolic AI, forming a discriminative counterpart to probabilistic-logical circuits such as ACs, SPNs, and PSDDs. We show that parameter learning for logistic circuits is convex optimization, and that a simple local search algorithm can induce strong model structures from data.

cs.LG↗

arXiv2018

A Semantic Loss Function for Deep Learning with Symbolic Knowledge

This paper develops a novel methodology for using symbolic knowledge in deep learning. From first principles, we derive a semantic loss function that bridges between neural output vectors and logical constraints. This loss function captures how close the neural network is to satisfying the constraints on its output. An experimental evaluation shows that it effectively guides the learner to achieve (near-)state-of-the-art results on semi-supervised multi-class classification. Moreover, it significantly increases the ability of the neural network to predict structured objects, such as rankings and paths. These discrete concepts are tremendously difficult to learn, and benefit from a tight integration of deep learning and symbolic reasoning methods.

cs.AI↗

arXiv2018

Inference Aided Reinforcement Learning for Incentive Mechanism Design in Crowdsourcing

Incentive mechanisms for crowdsourcing are designed to incentivize financially self-interested workers to generate and report high-quality labels. Existing mechanisms are often developed as one-shot static solutions, assuming a certain level of knowledge about worker models (expertise levels, costs of exerting efforts, etc.). In this paper, we propose a novel inference aided reinforcement mechanism that learns to incentivize high-quality data sequentially and requires no such prior assumptions. Specifically, we first design a Gibbs sampling augmented Bayesian inference algorithm to estimate workers' labeling strategies from the collected labels at each step. Then we propose a reinforcement incentive learning (RIL) method, building on top of the above estimates, to uncover how workers respond to different payments. RIL dynamically determines the payment without accessing any ground-truth labels. We theoretically prove that RIL is able to incentivize rational workers to provide high-quality labels. Empirical results show that our mechanism performs consistently well under both rational and non-fully rational (adaptive learning) worker models. Besides, the payments offered by RIL are more robust and have lower variances compared to the existing one-shot mechanisms.

cs.GT↗

arXiv2016

State of the Art Control of Atari Games Using Shallow Reinforcement Learning

The recently introduced Deep Q-Networks (DQN) algorithm has gained attention as one of the first successful combinations of deep neural networks and reinforcement learning. Its promise was demonstrated in the Arcade Learning Environment (ALE), a challenging framework composed of dozens of Atari 2600 games used to evaluate general competency in AI. It achieved dramatically better results than earlier approaches, showing that its ability to learn good representations is quite robust and general. This paper attempts to understand the principles that underlie DQN's impressive performance and to better contextualize its success. We systematically evaluate the importance of key representational biases encoded by DQN's network by proposing simple linear representations that make use of these concepts. Incorporating these characteristics, we obtain a computationally practical feature set that achieves competitive performance to DQN in the ALE. Besides offering insight into the strengths and weaknesses of DQN, we provide a generic representation for the ALE, significantly reducing the burden of learning a representation for each game. Moreover, we also provide a simple, reproducible benchmark for the sake of comparison to future work in the ALE.

cs.LG↗