Search Results for author:
Found 124 papers, 41 papers with code
Converging to Team-Maxmin Equilibria in Zero-Sum Multiplayer Games
Second, we design an ISG variant for TMEs (ISGT) by exploiting that a TME is an NE maximizing the team’s utility and show that ISGT converges to a TME and the impossibility of relaxing conditions in ISGT.
Skywork Open Reasoner 1 Technical Report
The success of DeepSeek-R1 underscores the significant role of reinforcement learning (RL) in enhancing the reasoning capabilities of large language models (LLMs).
MASLab: A Unified and Comprehensive Codebase for LLM-based Multi-Agent Systems
To address these challenges, we introduce MASLab, a unified, comprehensive, and research-friendly codebase for LLM-based MAS.
Enhance Mobile Agents Thinking Process Via Iterative Preference Learning
The Chain of Action-Planning Thoughts (CoaT) paradigm has been shown to improve the reasoning performance of VLM-based mobile agents in GUI tasks.
Mobile-Bench-v2: A More Realistic and Comprehensive Benchmark for VLM-based Mobile Agents
Additionally, both types of benchmarks fail to assess whether mobile agents can handle noise or engage in proactive interactions due to a lack of noisy apps or overly full instructions during the evaluation process.
Group-in-Group Policy Optimization for LLM Agent Training
In this work, we propose Group-in-Group Policy Optimization (GiGPO), a novel RL algorithm that achieves fine-grained credit assignment for LLM agents while preserving the appealing properties of group-based RL: critic-free, low memory, and stable convergence.
Establishing Linear Surrogate Regret Bounds for Convex Smooth Losses via Convolutional Fenchel-Young Losses
While convex smooth surrogate losses are appealing in particular due to the efficient estimation and optimization, the existence of a trade-off between the smoothness and linear regret bound has been believed in the community.
MF-LLM: Simulating Population Decision Dynamics via a Mean-Field Large Language Model Framework
To improve alignment with real-world data, we introduce IB-Tune, a novel fine-tuning method inspired by the Information Bottleneck principle, which retains population signals most predictive of future actions while filtering redundant history.
Guiding VLM Agents with Process Rewards at Inference Time for GUI Navigation
Recent advancements in visual language models (VLMs) have notably enhanced their capabilities in handling complex Graphical User Interface (GUI) interaction tasks.
A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment
Currently, existing surveys on LLM safety primarily focus on specific stages of the LLM lifecycle, e. g., deployment phase or fine-tuning phase, lacking a comprehensive understanding of the entire "lifechain" of LLMs.
Generative Auto-Bidding with Value-Guided Explorations
Auto-bidding, with its strong capability to optimize bidding decisions within dynamic and competitive online environments, has become a pivotal strategy for advertising platforms.
LLM$\times$MapReduce-V2: Entropy-Driven Convolutional Test-Time Scaling for Generating Long-Form Articles from Extremely Long Resources
Long-form generation is crucial for a wide range of practical applications, typically categorized into short-to-long and long-to-long generation.
From Understanding to Excelling: Template-Free Algorithm Design through Structural-Functional Co-Evolution
Large language models (LLMs) have greatly accelerated the automation of algorithm generation and optimization.
Policy Regularization on Globally Accessible States in Cross-Dynamics Reinforcement Learning
Additionally, as the environment dynamics change, certain expert states may become inaccessible, rendering their distributions less valuable for imitation.
LongSpec: Long-Context Speculative Decoding with Efficient Drafting and Verification
Despite its promise, the effective application of speculative decoding in LLMs still confronts three key challenges: the increasing memory demands of the draft model, the distribution shift between the short-training corpora and long-context inference, and inefficiencies in attention implementation.
Solving Urban Network Security Games: Learning Platform, Benchmark, and Challenge for AI Research
To facilitate the development of designing efficient learning algorithms for solving multiplayer games, we propose a multiplayer game platform for solving Urban Network Security Games (\textbf{UNSG}) that model real-world scenarios.
OpticalNet: An Optical Imaging Dataset and Benchmark Beyond the Diffraction Limit
Experimental results validate our "building block" concept, demonstrating that models trained on basic square units can effectively generalize to realistic, more complex unseen objects.
GAS: Generative Auto-bidding with Post-training Search
We use weak-to-strong search alignment by training small critics for different preferences and an MCTS-inspired search to refine the model's output.
MEMO: Memory-Guided Diffusion for Expressive Talking Video Generation
Recent advances in video diffusion models have unlocked new potential for realistic audio-driven talking video generation.
Mars-PO: Multi-Agent Reasoning System Preference Optimization
Mathematical reasoning is a fundamental capability for large language models (LLMs), yet achieving high performance in this domain remains a significant challenge.
Dual-Head Knowledge Distillation: Enhancing Logits Utilization with an Auxiliary Head
Drawing from the theoretical analysis, we propose a novel method called dual-head knowledge distillation, which partitions the linear classifier into two classification heads responsible for different losses, thereby preserving the beneficial effects of both losses on the backbone while eliminating adverse influences on the classification head.
MedGo: A Chinese Medical Large Language Model
Large models are a hot research topic in the field of artificial intelligence.
Double Oracle Neural Architecture Search for Game Theoretic Deep Learning Models
In this paper, we propose a new approach to train deep learning models using game theory concepts including Generative Adversarial Networks (GANs) and Adversarial Training (AT) where we deploy a double-oracle framework using best response oracles.
Computing Ex Ante Equilibrium in Heterogeneous Zero-Sum Team Games
Such insufficient policy expressiveness causes Team PSRO to be trapped into a sub-optimal ex ante equilibrium with significantly higher exploitability and never converges to the global ex ante equilibrium.
Deep Graph Anomaly Detection: A Survey and New Perspectives
To this end, in this work we aim to present a comprehensive review of deep learning approaches for GAD.
Resultant: Incremental Effectiveness on Likelihood for Unsupervised Out-of-Distribution Detection
Therefore, we appeal for more attention to incremental effectiveness on likelihood, i. e., whether a method could always surpass or at least match the performance of likelihood in U-OOD detection.
In-Context Exploiter for Extensive-Form Games
Nash equilibrium (NE) is a widely adopted solution concept in game theory due to its stability property.
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 $r_1$.
Q*: Improving Multi-step Reasoning for LLMs with Deliberative Planning
Large Language Models (LLMs) have demonstrated impressive capability in many natural language tasks.
MacroHFT: Memory Augmented Context-aware Reinforcement Learning On High Frequency Trading
To tackle these problems, we propose a novel Memory Augmented Context-aware Reinforcement learning method On HFT, \emph{a. k. a.}
Latent Logic Tree Extraction for Event Sequence Explanation from LLMs
In the E-step, we evaluate the posterior distribution over the latent logic trees using an LLM prior and the likelihood of the observed event sequences.
MANO: Exploiting Matrix Norm for Unsupervised Accuracy Estimation Under Distribution Shifts
Our findings motivate our proposed method MaNo which (1) applies a data-dependent normalization on the logits to reduce prediction bias, and (2) takes the $L_p$ norm of the matrix of normalized logits as the estimation score.
Resisting Stochastic Risks in Diffusion Planners with the Trajectory Aggregation Tree
As the structure evolves with the integration of new trajectories, unreliable states are marginalized, and the most impactful nodes are prioritized for decision-making.
Configurable Mirror Descent: Towards a Unification of Decision Making
Decision-making problems, categorized as single-agent, e. g., Atari, cooperative multi-agent, e. g., Hanabi, competitive multi-agent, e. g., Hold'em poker, and mixed cooperative and competitive, e. g., football, are ubiquitous in the real world.
vMFER: Von Mises-Fisher Experience Resampling Based on Uncertainty of Gradient Directions for Policy Improvement
Enhancing learning efficiency remains a key challenge in RL, with many efforts focused on using ensemble critics to boost policy evaluation efficiency.
S$^2$AC: Energy-Based Reinforcement Learning with Stein Soft Actor Critic
We derive a closed-form expression of the entropy of such policies.
Grasper: A Generalist Pursuer for Pursuit-Evasion Problems
Pursuit-evasion games (PEGs) model interactions between a team of pursuers and an evader in graph-based environments such as urban street networks.
Self-adaptive PSRO: Towards an Automatic Population-based Game Solver
(2) We propose the self-adaptive PSRO (SPSRO) by casting the hyperparameter value selection of the parametric PSRO as a hyperparameter optimization (HPO) problem where our objective is to learn an HPO policy that can self-adaptively determine the optimal hyperparameter values during the running of the parametric PSRO.
AgentStudio: A Toolkit for Building General Virtual Agents
General virtual agents need to handle multimodal observations, master complex action spaces, and self-improve in dynamic, open-domain environments.
Cradle: Empowering Foundation Agents Towards General Computer Control
To handle this issue, we propose the General Computer Control (GCC) setting to restrict foundation agents to interact with software through the most unified and standardized interface, i. e., using screenshots as input and keyboard and mouse actions as output.
A Multimodal Foundation Agent for Financial Trading: Tool-Augmented, Diversified, and Generalist
Notably, FinAgent is the first advanced multimodal foundation agent designed for financial trading tasks.
True Knowledge Comes from Practice: Aligning LLMs with Embodied Environments via Reinforcement Learning
Despite the impressive performance across numerous tasks, large language models (LLMs) often fail in solving simple decision-making tasks due to the misalignment of the knowledge in LLMs with environments.
Debiased Sample Selection for Combating Noisy Labels
To address this limitation, we propose a noIse-Tolerant Expert Model (ITEM) for debiased learning in sample selection.
Leveraging Gradients for Unsupervised Accuracy Estimation under Distribution Shift
Estimating the test performance of a model, possibly under distribution shift, without having access to the ground-truth labels is a challenging, yet very important problem for the safe deployment of machine learning algorithms in the wild.
Improving Unsupervised Hierarchical Representation with Reinforcement Learning
To address this issue we first analyze the shortcomings of existing methods for mitigating the "posterior collapse" from an information theory perspective then highlight the necessity of regularization for explicitly propagating data information to higher-level latent variables while maintaining the dependency between different levels.
keqing: knowledge-based question answering is a nature chain-of-thought mentor of LLM
Large language models (LLMs) have exhibited remarkable performance on various natural language processing (NLP) tasks, especially for question answering.
Reinforcement Learning with Maskable Stock Representation for Portfolio Management in Customizable Stock Pools
Specifically, the target stock pool of different investors varies dramatically due to their discrepancy on market states and individual investors may temporally adjust stocks they desire to trade (e. g., adding one popular stocks), which lead to customizable stock pools (CSPs).
AURO: Reinforcement Learning for Adaptive User Retention Optimization in Recommender Systems
As the policy performance of RL is sensitive to environment drifts, the loss function enables the state abstraction to be reflective of environment changes and notify the recommendation policy to adapt accordingly.
EarnHFT: Efficient Hierarchical Reinforcement Learning for High Frequency Trading
In stage II, we construct a pool of diverse RL agents for different market trends, distinguished by return rates, where hundreds of RL agents are trained with different preferences of return rates and only a tiny fraction of them will be selected into the pool based on their profitability.
Market-GAN: Adding Control to Financial Market Data Generation with Semantic Context
Financial simulators play an important role in enhancing forecasting accuracy, managing risks, and fostering strategic financial decision-making.
Efficient Last-iterate Convergence Algorithms in Solving Games
To establish last-iterate convergence for Counterfactual Regret Minimization (CFR) algorithms in learning a Nash equilibrium (NE) of extensive-form games (EFGs), recent studies reformulate learning an NE of the original EFG as learning the NEs of a sequence of (perturbed) regularized EFGs.
IMM: An Imitative Reinforcement Learning Approach with Predictive Representation Learning for Automatic Market Making
Market making (MM) has attracted significant attention in financial trading owing to its essential function in ensuring market liquidity.
Weakly Supervised Regression with Interval Targets
Third, we propose a statistically consistent limiting method for RIT to train the model by limiting the predictions to the interval.
Partial-Label Regression
Our proposed methods are theoretically grounded and can be compatible with any models, optimizers, and losses.
Synapse: Trajectory-as-Exemplar Prompting with Memory for Computer Control
To address these challenges, we introduce Synapse, a computer agent featuring three key components: i) state abstraction, which filters out task-irrelevant information from raw states, allowing more exemplars within the limited context, ii) trajectory-as-exemplar prompting, which prompts the LLM with complete trajectories of the abstracted states and actions to improve multi-step decision-making, and iii) exemplar memory, which stores the embeddings of exemplars and retrieves them via similarity search for generalization to novel tasks.
State Regularized Policy Optimization on Data with Dynamics Shift
Data with dynamics shift are separated according to their environment parameters to train the corresponding policy.
Towards Skilled Population Curriculum for Multi-Agent Reinforcement Learning
Despite its success, ACL's applicability is limited by (1) the lack of a general student framework for dealing with the varying number of agents across tasks and the sparse reward problem, and (2) the non-stationarity of the teacher's task due to ever-changing student strategies.
Multi-agent Reinforcement Learning
reinforcement-learning
+2
Population-size-Aware Policy Optimization for Mean-Field Games
In this work, we attempt to bridge the two fields of finite-agent and infinite-agent games, by studying how the optimal policies of agents evolve with the number of agents (population size) in mean-field games, an agent-centric perspective in contrast to the existing works focusing typically on the convergence of the empirical distribution of the population.
Attacking Cooperative Multi-Agent Reinforcement Learning by Adversarial Minority Influence
To achieve maximum deviation in victim policies under complex agent-wise interactions, our unilateral attack aims to characterize and maximize the impact of the adversary on the victims.
Reinforcement Learning from Diverse Human Preferences
The complexity of designing reward functions has been a major obstacle to the wide application of deep reinforcement learning (RL) techniques.
PRUDEX-Compass: Towards Systematic Evaluation of Reinforcement Learning in Financial Markets
Specifically, i) we propose AlphaMix+ as a strong FinRL baseline, which leverages mixture-of-experts (MoE) and risk-sensitive approaches to make diversified risk-aware investment decisions, ii) we evaluate 8 FinRL methods in 4 long-term real-world datasets of influential financial markets to demonstrate the usage of our PRUDEX-Compass, iii) PRUDEX-Compass together with 4 real-world datasets, standard implementation of 8 FinRL methods and a portfolio management environment is released as public resources to facilitate the design and comparison of new FinRL methods.
Mitigating Memorization of Noisy Labels by Clipping the Model Prediction
In the presence of noisy labels, designing robust loss functions is critical for securing the generalization performance of deep neural networks.
PrefRec: Recommender Systems with Human Preferences for Reinforcing Long-term User Engagement
Though promising, the application of RL heavily relies on well-designed rewards, but designing rewards related to long-term user engagement is quite difficult.
Generalized Consistent Multi-Class Classification with Rejection to be Compatible with Arbitrary Losses
\emph{Classification with rejection} (CwR) refrains from making a prediction to avoid critical misclassification when encountering test samples that are difficult to classify.
Classifying Ambiguous Identities in Hidden-Role Stochastic Games with Multi-Agent Reinforcement Learning
In this work, we develop a novel identity detection reinforcement learning (IDRL) framework that allows an agent to dynamically infer the identities of nearby agents and select an appropriate policy to accomplish the task.
Multi-agent Reinforcement Learning
reinforcement-learning
+2
RPM: Generalizable Behaviors for Multi-Agent Reinforcement Learning
Despite the recent advancement in multi-agent reinforcement learning (MARL), the MARL agents easily overfit the training environment and perform poorly in the evaluation scenarios where other agents behave differently.
Multi-agent Reinforcement Learning
reinforcement-learning
+2
Deep Attentive Belief Propagation: Integrating Reasoning and Learning for Solving Constraint Optimization Problems
Belief Propagation (BP) is an important message-passing algorithm for various reasoning tasks over graphical models, including solving the Constraint Optimization Problems (COPs).
Offline Equilibrium Finding
Extensive experimental results demonstrate the superiority of our approach over offline RL algorithms and the importance of using model-based methods for OEF problems.
Open-Sampling: Exploring Out-of-Distribution data for Re-balancing Long-tailed datasets
Deep neural networks usually perform poorly when the training dataset suffers from extreme class imbalance.
Quantitative Stock Investment by Routing Uncertainty-Aware Trading Experts: A Multi-Task Learning Approach
To tackle these two limitations, we first reformulate quantitative investment as a multi-task learning problem.
ResAct: Reinforcing Long-term Engagement in Sequential Recommendation with Residual Actor
Meanwhile, reinforcement learning (RL) is widely regarded as a promising framework for optimizing long-term engagement in sequential recommendation.
Off-Beat Multi-Agent Reinforcement Learning
During execution durations, the environment changes are influenced by, but not synchronised with, action execution.
Multi-agent Reinforcement Learning
reinforcement-learning
+4
Mitigating Neural Network Overconfidence with Logit Normalization
Our method is motivated by the analysis that the norm of the logit keeps increasing during training, leading to overconfident output.
NSGZero: Efficiently Learning Non-Exploitable Policy in Large-Scale Network Security Games with Neural Monte Carlo Tree Search
Second, we enable neural MCTS with decentralized control, making NSGZero applicable to NSGs with many resources.
GearNet: Stepwise Dual Learning for Weakly Supervised Domain Adaptation
Although there have been a few studies on this problem, most of them only exploit unidirectional relationships from the source domain to the target domain.
DeepScalper: A Risk-Aware Reinforcement Learning Framework to Capture Fleeting Intraday Trading Opportunities
Reinforcement learning (RL) techniques have shown great success in many challenging quantitative trading tasks, such as portfolio management and algorithmic trading.
Pretrained Cost Model for Distributed Constraint Optimization Problems
Our model, GAT-PCM, is then pretrained with optimally labelled data in an offline manner, so as to construct effective heuristics to boost a broad range of DCOP algorithms where evaluating the quality of a partial assignment is critical, such as local search or backtracking search.
RMIX: Learning Risk-Sensitive Policies forCooperative Reinforcement Learning Agents
Current value-based multi-agent reinforcement learning methods optimize individual Q values to guide individuals' behaviours via centralized training with decentralized execution (CTDE).
Open-sampling: Re-balancing Long-tailed Datasets with Out-of-Distribution Data
Deep neural networks usually perform poorly when the training dataset suffers from extreme class imbalance.
Learning Pseudometric-based Action Representations for Offline Reinforcement Learning
Offline reinforcement learning is a promising approach for practical applications since it does not require interactions with real-world environments.
Online Ad Hoc Teamwork under Partial Observability
Autonomous agents often need to work together as a team to accomplish complex cooperative tasks.
Reinforcement Learning for Quantitative Trading
RL's impact is pervasive, recently demonstrating its ability to conquer many challenging QT tasks.
Mis-spoke or mis-lead: Achieving Robustness in Multi-Agent Communicative Reinforcement Learning
Empirical results demonstrate that many state-of-the-art MACRL methods are vulnerable to message attacks, and our method can significantly improve their robustness.
Multi-agent Reinforcement Learning
reinforcement-learning
+2
Open-set Label Noise Can Improve Robustness Against Inherent Label Noise
Learning with noisy labels is a practically challenging problem in weakly supervised learning.
Multi-Class Classification from Single-Class Data with Confidences
We show that without any assumptions on the loss functions, models, and optimizers, we can successfully learn a multi-class classifier from only data of a single class with a rigorous consistency guarantee when confidences (i. e., the class-posterior probabilities for all the classes) are available.
Contingency-Aware Influence Maximization: A Reinforcement Learning Approach
Empirical results show that our method achieves influence as high as the state-of-the-art methods for contingency-aware IM, while having negligible runtime at test phase.
On the Robustness of Average Losses for Partial-Label Learning
Partial-label learning (PLL) utilizes instances with PLs, where a PL includes several candidate labels but only one is the true label (TL).
Solving Large-Scale Extensive-Form Network Security Games via Neural Fictitious Self-Play
Securing networked infrastructures is important in the real world.
CFR-MIX: Solving Imperfect Information Extensive-Form Games with Combinatorial Action Space
The challenge of solving this type of game is that the team's joint action space grows exponentially with the number of agents, which results in the inefficiency of the existing algorithms, e. g., Counterfactual Regret Minimization (CFR).
L2E: Learning to Exploit Your Opponent
In this work, we propose a novel Learning to Exploit (L2E) framework for implicit opponent modeling.
DO-GAN: A Double Oracle Framework for Generative Adversarial Networks
In this paper, we propose a new approach to train Generative Adversarial Networks (GANs) where we deploy a double-oracle framework using the generator and discriminator oracles.
RMIX: Learning Risk-Sensitive Policies for Cooperative Reinforcement Learning Agents
Current value-based multi-agent reinforcement learning methods optimize individual Q values to guide individuals' behaviours via centralized training with decentralized execution (CTDE).
Learning from Similarity-Confidence Data
Weakly supervised learning has drawn considerable attention recently to reduce the expensive time and labor consumption of labeling massive data.
Safe Coupled Deep Q-Learning for Recommendation Systems
Firstly, we introduce a novel training scheme with two value functions to maximize the accumulated long-term reward under the safety constraint.
RMIX: Risk-Sensitive Multi-Agent Reinforcement Learning
Centralized training with decentralized execution (CTDE) has become an important paradigm in multi-agent reinforcement learning (MARL).
Multi-agent Reinforcement Learning
reinforcement-learning
+4
Deep Stock Trading: A Hierarchical Reinforcement Learning Framework for Portfolio Optimization and Order Execution
Portfolio management via reinforcement learning is at the forefront of fintech research, which explores how to optimally reallocate a fund into different financial assets over the long term by trial-and-error.
Personalized Adaptive Meta Learning for Cold-start User Preference Prediction
Recently, many existing studies regard the cold-start personalized preference prediction as a few-shot learning problem, where each user is the task and recommended items are the classes, and the gradient-based meta learning method (MAML) is leveraged to address this challenge.
MetaInfoNet: Learning Task-Guided Information for Sample Reweighting
Deep neural networks have been shown to easily overfit to biased training data with label noise or class imbalance.
Efficient Reservoir Management through Deep Reinforcement Learning
Dams impact downstream river dynamics through flow regulation and disruption of upstream-downstream linkages.
SpotTune: Leveraging Transient Resources for Cost-efficient Hyper-parameter Tuning in the Public Cloud
Hyper-parameter tuning (HPT) is crucial for many machine learning (ML) algorithms.
SemiNLL: A Framework of Noisy-Label Learning by Semi-Supervised Learning
We also instantiate our framework with different combinations, which set the new state of the art on benchmark-simulated and real-world datasets with noisy labels.
Enhancing Neural Models with Vulnerability via Adversarial Attack
2) There is no previous work considering adversarial attack to improve the performance of NLSM tasks.
Pointwise Binary Classification with Pairwise Confidence Comparisons
To alleviate the data requirement for training effective binary classifiers in binary classification, many weakly supervised learning settings have been proposed.
Complexity and Algorithms for Exploiting Quantal Opponents in Large Two-Player Games
This paper aims to analyze and propose scalable algorithms for computing effective and robust strategies against a quantal opponent in normal-form and extensive-form games.
Learning to Collaborate in Multi-Module Recommendation via Multi-Agent Reinforcement Learning without Communication
Thus, the global policy of the whole page could be sub-optimal.
Multi-agent Reinforcement Learning
Reinforcement Learning (RL)
Contextual User Browsing Bandits for Large-Scale Online Mobile Recommendation
First, since we concern the reward of a set of recommended items, we model the online recommendation as a contextual combinatorial bandit problem and define the reward of a recommended set.
Provably Consistent Partial-Label Learning
Partial-label learning (PLL) is a multi-class classification problem, where each training example is associated with a set of candidate labels.
Learning Behaviors with Uncertain Human Feedback
However, previous works rarely consider the uncertainty when humans provide feedback, especially in cases that the optimal actions are not obvious to the trainers.
Learning Expensive Coordination: An Event-Based Deep RL Approach
The main difficulties of expensive coordination are that i) the leader has to consider the long-term effect and predict the followers' behaviors when assigning bonuses and ii) the complex interactions between followers make the training process hard to converge, especially when the leader's policy changes with time.
Combating noisy labels by agreement: A joint training method with co-regularization
The state-of-the-art approaches "Decoupling" and "Co-teaching+" claim that the "disagreement" strategy is crucial for alleviating the problem of learning with noisy labels.
Ranked #11 on
Learning with noisy labels
on CIFAR-10N-Random3
Learning with Multiple Complementary Labels
In this paper, we propose a novel problem setting to allow MCLs for each example and two ways for learning with MCLs.
Inducing Cooperation via Team Regret Minimization based Multi-Agent Deep Reinforcement Learning
Existing value-factorized based Multi-Agent deep Reinforce-ment Learning (MARL) approaches are well-performing invarious multi-agent cooperative environment under thecen-tralized training and decentralized execution(CTDE) scheme, where all agents are trained together by the centralized valuenetwork and each agent execute its policy independently.
Learning Efficient Multi-agent Communication: An Information Bottleneck Approach
Under the limited bandwidth constraint, a communication protocol is required to generate informative messages.
Multi-agent Reinforcement Learning
Reinforcement Learning
+1
EUSP: An Easy-to-Use Semantic Parsing PlatForm
Semantic parsing aims to map natural language utterances into structured meaning representations.
Manipulating a Learning Defender and Ways to Counteract
We then apply a game-theoretic framework at a higher level to counteract such manipulation, in which the defender commits to a policy that specifies her strategy commitment according to the learned information.
Competitive Bridge Bidding with Deep Neural Networks
Second, based on the analysis of the impact of other players' unknown cards on one's final rewards, we design two neural networks to deal with imperfect information, the first one inferring the cards of the partner and the second one taking the outputs of the first one as part of its input to select a bid.
Partial Label Learning with Self-Guided Retraining
We show that optimizing this convex-concave problem is equivalent to solving a set of quadratic programming (QP) problems.
Collaboration based Multi-Label Learning
It is well-known that exploiting label correlations is crucially important to multi-label learning.
Sentence Rewriting for Semantic Parsing
A major challenge of semantic parsing is the vocabulary mismatch problem between natural language and target ontology.
Model-Free Context-Aware Word Composition
Word composition is a promising technique for representation learning of large linguistic units (e. g., phrases, sentences and documents).
Semi-Supervised Lexicon Learning for Wide-Coverage Semantic Parsing
Semantic parsers critically rely on accurate and high-coverage lexicons.
Accurate Text-Enhanced Knowledge Graph Representation Learning
Previous representation learning techniques for knowledge graph representation usually represent the same entity or relation in different triples with the same representation, without considering the ambiguity of relations and entities.
Vehicle Traffic Driven Camera Placement for Better Metropolis Security Surveillance
Security surveillance is one of the most important issues in smart cities, especially in an era of terrorism.
