United States

The reward signal plays a central role in defining the desired behaviors of agents in reinforcement learning (RL). Rewards collected from realistic environments could be perturbed, corrupted, or noisy due to an adversary, sensor error, or because they come from subjective human feedback. Thus, it is important to construct agents that can learn under such rewards. Existing methodologies for this problem make strong assumptions, including that the perturbation is known in advance, clean rewards are accessible, or that the perturbation preserves the optimal policy. We study a new, more general, class of unknown perturbations, and introduce a distributional reward critic framework for estimating reward distributions and perturbations during training. Our proposed methods are compatible with any RL algorithm. Despite their increased generality, we show that they achieve comparable or better rewards than existing methods in a variety of environments, including those with clean rewards. Under the challenging and generalized perturbations we study, we win/tie the highest return in 44/48 tested settings (compared to 11/48 for the best baseline). Our results broaden and deepen our ability to perform RL in reward-perturbed environments.

AAAI 2025

The Distributional Reward Critic Framework for Reinforcement Learning Under Perturbed Rewards

reinforcement learning

## Welcome to EMNLP 2024! 
We are excited to welcome you to one of the most prominent conferences in the field of Natural Language Processing. This year, EMNLP 2024 is being held in a hybrid format,
offering both virtual and in-person participation in beautiful Miami. Due to a record-breaking number of submissions, we've expanded the total number of accepted papers to accommodate more cutting-edge research from around the globe.
### [Conference Handbook](https://drive.google.com/file/d/1WPROgxjLAC96AJL7Ugy0tEnYm7dkrbHt/view?usp=sharing)

You are required to register for this event. **Please register [here](https://2024.emnlp.org/registration/).** The EMNLP 2024 event page on Underline will be open to public one week prior to the event.

Please register!

EMNLP 2024

EMNLP 2024 will take place in Miami, Florida from Nov 12th to Nov 16th, 2024, at the Hyatt Regency Miami Hote and on Underline for remote participants.

poster

We are pleased to announce the Thirty-Ninth AAAI Conference on Artificial Intelligence (AAAI-25), which will be held in Philadelphia, Pennsylvania at the Pennsylvania Convention Center from February 25 to March 4, 2025.

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-25 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.

### [Invited Speakers](https://aaai.org/conference/aaai/aaai-25/aaai-25-invited-speakers/)

Register [here](https://aaai.org/conference/aaai/aaai-25/registration/)

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-25 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.



Causal learning relies on the computationally demanding task of estimating causal graphs. In this paper, a new divide-and-conquer approach called DCILP is proposed for causal graph learning. The divide phase proceeds by identifying the Markov blanket MB$(X_i)$ of each variable $X_i$, and then addressing simultaneously the subproblems restricted on each MB$(X_i)$. Each subproblem benefits from a more favorable ratio between the number of data samples and the number of variables considered; however, it is adversely affected by the presence of hidden confounders (as variables external to MB$(X_i)$ might influence the variables inside). 
The novelty of DCILP lies in the conquer phase, which tackles the problem of aggregating the local causal graphs from the divide phase. Such an aggregation is a challenging combinatorial optimization problem especially in large-scale applications. We show that this aggregation can be formulated as an integer linear programming (ILP) problem, which is delegated to an ILP solver. Through experiments and comparisons with state-of-the-art methods, the proposed approach demonstrates comparable or improved learning accuracy while achieving significant improvements in terms of scalability in the graph size.

DCILP: A Distributed Approach for Large-Scale Causal Structure Learning

Time series forecasting requires reliable uncertainty estimates. Gaussian process regression provides a powerful framework for modelling this in a probabilistic fashion. However, its application to large time series is challenging, due to its cubic time complexity and quadratic memory requirement. In this work, we present KernelMatmul, a novel method that accelerates Gaussian process inference and thus facilitates scaling of Gaussian process regression to large, irregularly sampled and multi-output time series. Leveraging conjugate gradients in combination with sparsity approximation, KernelMatmul achieves time and memory complexity linear in the number of samples. We thoroughly benchmark our new method against multiple baselines to demonstrate its benefits and limitations, both in efficiency and accuracy.

KernelMatmul: Scaling Gaussian Processes to Large Time Series

We present and release MIDI-GPT, a generative system based on the Transformer architecture that is designed for computer-assisted music composition workflows. MIDI-GPT supports the infilling of musical material at the track and bar level, and can condition generation on particular attributes including: instrument type, musical style, note density, polyphony level, and note duration. In order to integrate these features, we employ an alternative representation for musical material, creating a time-ordered sequence of musical events for each track and concatenating several tracks into a single sequence, rather than using a single time-ordered sequence where the musical events corresponding to different tracks are interleaved. We also propose a variation of our representation allowing for expressiveness. We present experimental results that demonstrate that MIDI-GPT is able to consistently avoid duplicating the musical material it was trained on, generate music that is stylistically similar to the training dataset, and that attribute controls allow enforcing various constraints on the generated material. We also outline several real-world applications of MIDI-GPT, including collaborations with industry partners that explore integrating and evaluating MIDI-GPT, into real-world products, as well as several artistic works produced using it.

MIDI-GPT: A Controllable Generative Model for Computer-Assisted Multitrack Music Composition

Continuous control tasks often involve high-dimensional, dynamic, and non-linear environments. State-of-the-art performance in these tasks is achieved through complex black-box policies that are effective, but suffer from an inherent opacity. Interpretable policies, while generally underperforming compared to their black-box counterparts, advantageously facilitate transparent decision-making within automated systems. Hence, their usage is often essential for diagnosing and mitigating errors, supporting ethical and legal accountability, and fostering trust among stakeholders. In this paper, we propose SMoSE, a novel method to train sparsely activated interpretable controllers, based on a top-1 Mixture-of-Experts architecture. SMoSE combines a set of interpretable decision-makers, trained to be experts in different basic skills, and an interpretable router that assigns tasks among the experts. The training is carried out via state-of-the-art Reinforcement Learning algorithms, exploiting load-balancing techniques to ensure fair expert usage. We then distill decision trees from the weights of the router, significantly improving the ease of interpretation. We evaluate SMoSE on six benchmark environments from MuJoCo: our method outperforms recent interpretable baselines and narrows the gap with non-interpretable state-of-the-art algorithms.

SMoSE: Sparse Mixture of Shallow Experts for Interpretable Reinforcement Learning in Continuous Control Tasks

Multimodal large language models (MLLMs) can simultaneously process visual, textual, and auditory data, capturing insights that complement human analysis. 
However, existing video question-answering (VidQA) benchmarks and datasets often exhibit a bias toward a single modality, despite the goal of requiring advanced reasoning skills that integrate diverse modalities to answer the queries.

In this work, we introduce the modality importance score (MIS) to identify such bias. It is designed to assess which modality embeds the necessary information to answer the question. 
Additionally, we propose an innovative method using state-of-the-art MLLMs to estimate the modality importance, which can serve as a proxy for human judgments of modality perception.
With this MIS, we demonstrate the presence of unimodal bias and the scarcity of genuinely multimodal questions in existing datasets. 
We further validate the modality importance score with multiple ablation studies to evaluate the performance of MLLMs on permuted feature sets. 
Our results indicate that current models do not effectively integrate information due to modality imbalance in existing datasets. 
Our proposed MLLM-derived MIS can guide the curation of modality-balanced datasets that advance multimodal learning and enhance MLLMs' capabilities to understand and utilize synergistic relations across modalities.

Assessing Modality Bias in Video Question Answering Benchmarks with Multimodal Large Language Models

Generation of 3D human motion holds significant importance in the creative industry. While recent notable advances have been made in generating common motions, existing methods struggle to generate diverse and rare motions due to the complexity of motions and limited training data. This work introduces ReMoGPT, a unified motion-language generative model that solves a wide range of motion-related tasks by incorporating a multi-modal retrieval mechanism into the generation process to address the limitations of existing models, namely diversity and generalizability. We propose to focus on body-part-level motion features to enable fine-grained text-motion retrieval and locate suitable references from the database to conduct generation. Then, the motion-language generative model is trained with prompt-based question-and-answer tasks designed for different motion-relevant problems. We incorporate the retrieved samples into the prompt, and then perform instruction tuning of the motion-language model, to learn from task feedback and produce promising results with the help of fine-grained multi-modal retrieval. Extensive experiments validate the efficacy of ReMoGPT, showcasing its superiority over existing state-of-the-art methods. The framework performs well on multiple motion tasks, including motion retrieval, generation, and captioning.

ReMoGPT: Part-Level Retrieval-Augmented Motion-Language Models

Large Language Models (LLMs) have shown remarkable performance across various tasks, but the escalating demands on computational resources pose significant challenges, particularly in the extensive utilization of full fine-tuning for downstream tasks. To address this, parameter-efficient fine-tuning (PEFT) methods have been developed, but they often underperform compared to full fine-tuning and struggle with memory efficiency. In this work, we introduce Gradient Weight-Normalized Low-Rank Projection (GradNormLoRP), a novel approach that enhances both parameter and memory efficiency while maintaining comparable performance to full fine-tuning. GradNormLoRP normalizes the weight matrix to improve gradient conditioning, facilitating better convergence during optimization. Additionally, it applies low-rank approximations to the weight and gradient matrices, significantly reducing memory usage during training. Extensive experiments demonstrate that our 8-bit GradNormLoRP reduces optimizer memory usage by up to 89.5\% and enables the pre-training of large LLMs, such as LLaMA 7B, on consumer-level GPUs like the NVIDIA RTX 4090, without additional inference costs. Moreover, GradNormLoRP outperforms existing low-rank methods in fine-tuning tasks. For instance, when fine-tuning the RoBERTa model on all GLUE tasks with a rank of 8, GradNormLoRP achieves an average score of 80.65, surpassing LoRA's score of 79.23. These results underscore GradNormLoRP as a promising alternative for efficient LLM pre-training and fine-tuning.  
The source code will be made publicly available to support the LLM community.

Gradient Weight-normalized Low-rank Projection for Efficient LLM Training

This paper introduces state abstraction for two-player zero-sum Markov games (TZMGs) where the payoffs for the two players are determined by the state representing the environment and their respective actions, with state transitions following a Markov decision processes (MDPs). For example, in games like soccer, the value of actions changes according to the state of play, we should describe them as Markov games. In TZMGs, the more the number of states becomes, the more difficult computing the equilibrium becomes. Therefore, we abstract the states of TZMGs and examine the performance. State abstraction reduces the number of states by treating multiple different states as a single state, and there is a substantial body of research on finding optimal policies for Markov decision processes using state abstraction. This study extends the state abstraction for MDPs to Markov games. In this case, the game with state abstraction may yield different equilibrium solutions from those of the ground game. To evaluate the equilibrium solutions of the game with state abstraction, we derived bounds on duality gap, which represents the distance from the equilibrium solutions of the ground game. Finally, we demonstrate our state abstraction with Markov Soccer, compute equilibrium policies, and examine the results.

Approximate State Abstraction for Markov Games

Black box optimization (BBO) focuses on optimizing unknown functions in high-dimensional spaces. In many applications, sampling the unknown function is expensive, imposing a tight sample budget.Ongoing work is making progress on reducing the sample budget by learning the shape/structure of the function, known as kernel learning.
We propose a new method to learn the kernel of a Gaussian Process. Our idea is to create a continuous kernel space in the latent space of a variational autoencoder, and run an auxiliary optimization to identify the best kernel. Results show that the proposed method, {\em Kernel Optimized Blackbox Optimization} (KOBO), outperforms state of the art by estimating the optimal at considerably lower sample budgets.
Results hold not only across synthetic benchmark functions but also in real applications. We show that a hearing aid may be personalized with fewer audio queries to the user, or a generative model could converge to desirable images from limited user ratings.

Kernel Learning for Sample Constrained Black-Box Optimization

Video inpainting is a crucial task with diverse applications, including fine-grained video editing, video recovery, and video dewatermarking. However, most existing video inpainting methods primarily focus on visual content completion while neglecting text information. There are only a limited number of text-guided video inpainting techniques, and these techniques struggle with maintaining visual quality and exhibit poor semantic representation capabilities. In this paper, we introduce CoCoCo, a text-guided video inpainting diffusion framework. To address the aforementioned challenges, we enhance both the training data and model structure. Specifically, we devise an instance-aware region selection strategy for masked area sampling and develop a novel motion block that incorporates efficient 3D full attention and textual cross attention. Additionally, our CoCoCo framework can be seamlessly integrated with various personalized text-to-image diffusion models through a delicate training-free transfer mechanism. Comprehensive experiments demonstrate that CoCoCo can create high-quality visual content with enhanced temporal consistency, improved text controllability, and better compatibility with personalized image models.

Downloads

Next from AAAI 2025

DCILP: A Distributed Approach for Large-Scale Causal Structure Learning

Similar lecture

Enhancing Reinforcement Learning with Intrinsic Rewards from Language Model Critique

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES