Search Results for author:
Found 29 papers, 11 papers with code
Multi-agent Embodied AI: Advances and Future Directions
Embodied artificial intelligence (Embodied AI) plays a pivotal role in the application of advanced technologies in the intelligent era, where AI systems are integrated with physical bodies that enable them to perceive, reason, and interact with their environments.
HyperZero: A Customized End-to-End Auto-Tuning System for Recommendation with Hourly Feedback
Modern recommendation systems can be broadly divided into two key stages: the ranking stage, where the system predicts various user engagements (e. g., click-through rate, like rate, follow rate, watch time), and the value model stage, which aggregates these predictive scores through a function (e. g., a linear combination defined by a weight vector) to measure the value of each content by a single numerical score.
SkillTree: Explainable Skill-Based Deep Reinforcement Learning for Long-Horizon Control Tasks
To achieve explainability, decision trees have emerged as a popular and promising alternative to neural networks.
Stable Continual Reinforcement Learning via Diffusion-based Trajectory Replay
Given the inherent non-stationarity prevalent in real-world applications, continual Reinforcement Learning (RL) aims to equip the agent with the capability to address a series of sequentially presented decision-making tasks.
Q-Adapter: Customizing Pre-trained LLMs to New Preferences with Forgetting Mitigation
Thanks to the residual Q-learning framework, we can restore the customized LLM with the pre-trained LLM and the \emph{residual Q-function} without the reward function $r_1$.
Disentangling Policy from Offline Task Representation Learning via Adversarial Data Augmentation
Specifically, the objective of adversarial data augmentation is not merely to generate data analogous to offline data distribution; instead, it aims to create adversarial examples designed to confound learned task representations and lead to incorrect task identification.
Debiased Offline Representation Learning for Fast Online Adaptation in Non-stationary Dynamics
DORA incorporates an information bottleneck principle that maximizes mutual information between the dynamics encoding and the environmental data, while minimizing mutual information between the dynamics encoding and the actions of the behavior policy.
Efficient Human-AI Coordination via Preparatory Language-based Convention
Developing intelligent agents capable of seamless coordination with humans is a critical step towards achieving artificial general intelligence.
Robust multi-agent coordination via evolutionary generation of auxiliary adversarial attackers
Concretely, to avoid the ego-system overfitting to a specific attacker, we maintain a set of attackers, which is optimized to guarantee the attackers high attacking quality and behavior diversity.
Communication-Robust Multi-Agent Learning by Adaptable Auxiliary Multi-Agent Adversary Generation
In specific, we introduce a novel message-attacking approach that models the learning of the auxiliary attacker as a cooperative problem under a shared goal to minimize the coordination ability of the ego system, with which every information channel may suffer from distinct message attacks.
Multi-agent Continual Coordination via Progressive Task Contextualization
Towards tackling the mentioned issue, this paper proposes an approach Multi-Agent Continual Coordination via Progressive Task Contextualization, dubbed MACPro.
Robust Multi-agent Communication via Multi-view Message Certification
Many multi-agent scenarios require message sharing among agents to promote coordination, hastening the robustness of multi-agent communication when policies are deployed in a message perturbation environment.
Efficient Communication via Self-supervised Information Aggregation for Online and Offline Multi-agent Reinforcement Learning
We also release the built offline benchmarks in this paper as a testbed for communication ability validation to facilitate further future research.
Multi-agent Dynamic Algorithm Configuration
MA-DAC formulates the dynamic configuration of a complex algorithm with multiple types of hyperparameters as a contextual multi-agent Markov decision process and solves it by a cooperative multi-agent RL (MARL) algorithm.
Heterogeneous Multi-agent Zero-Shot Coordination by Coevolution
Generating agents that can achieve zero-shot coordination (ZSC) with unseen partners is a new challenge in cooperative multi-agent reinforcement learning (MARL).
Model Generation with Provable Coverability for Offline Reinforcement Learning
Model-based offline optimization with dynamics-aware policy provides a new perspective for policy learning and out-of-distribution generalization, where the learned policy could adapt to different dynamics enumerated at the training stage.
LPFS: Learnable Polarizing Feature Selection for Click-Through Rate Prediction
When training is finished, some gates are exact zero, while others are around one, which is particularly favored by the practical hot-start training in the industry, due to no damage to the model performance before and after removing the features corresponding to exact-zero gates.
A Neural Network Architecture for Program Understanding Inspired by Human Behaviors
In this paper, we consider human behaviors and propose the PGNN-EK model that consists of two main components.
Multi-Agent Policy Transfer via Task Relationship Modeling
We demonstrate that the task representation can capture the relationship among tasks, and can generalize to unseen tasks.
Persia: An Open, Hybrid System Scaling Deep Learning-based Recommenders up to 100 Trillion Parameters
Specifically, in order to ensure both the training efficiency and the training accuracy, we design a novel hybrid training algorithm, where the embedding layer and the dense neural network are handled by different synchronization mechanisms; then we build a system called Persia (short for parallel recommendation training system with hybrid acceleration) to support this hybrid training algorithm.
LINDA: Multi-Agent Local Information Decomposition for Awareness of Teammates
During long-time observations, agents can build \textit{awareness} for teammates to alleviate the problem of partial observability.
PASTO: Strategic Parameter Optimization in Recommendation Systems -- Probabilistic is Better than Deterministic
In this setting with multiple and constrained goals, this paper discovers that a probabilistic strategic parameter regime can achieve better value compared to the standard regime of finding a single deterministic parameter.
Rank the Episodes: A Simple Approach for Exploration in Procedurally-Generated Environments
Unfortunately, methods based on intrinsic rewards often fall short in procedurally-generated environments, where a different environment is generated in each episode so that the agent is not likely to visit the same state more than once.
Short Video-based Advertisements Evaluation System: Self-Organizing Learning Approach
In this paper, we proposed a novel end-to-end self-organizing framework for user behavior prediction.
Themes Informed Audio-visual Correspondence Learning
The applications of short-term user-generated video (UGV), such as Snapchat, and Youtube short-term videos, booms recently, raising lots of multimodal machine learning tasks.
$\texttt{DeepSqueeze}$: Decentralization Meets Error-Compensated Compression
Since the \emph{decentralized} training has been witnessed to be superior to the traditional \emph{centralized} training in the communication restricted scenario, therefore a natural question to ask is "how to apply the error-compensated technology to the decentralized learning to further reduce the communication cost."
Dictionary LASSO: Guaranteed Sparse Recovery under Linear Transformation
Specifically, we show 1) in the noiseless case, if the condition number of $D$ is bounded and the measurement number $n\geq \Omega(s\log(p))$ where $s$ is the sparsity number, then the true solution can be recovered with high probability; and 2) in the noisy case, if the condition number of $D$ is bounded and the measurement increases faster than $s\log(p)$, that is, $s\log(p)=o(n)$, the estimate error converges to zero with probability 1 when $p$ and $s$ go to infinity.
Efficient Methods for Overlapping Group Lasso
There have been several recent attempts to study a more general formulation, where groups of features are given, potentially with overlaps between the groups.
