Search Results for author:
Found 56 papers, 9 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.
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.
ResAct: Reinforcing Long-term Engagement in Sequential Recommendation with Residual Actor
However, due to expensive online interactions, it is very difficult for RL algorithms to perform state-action value estimation, exploration and feature extraction when optimizing long-term engagement.
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
+2
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 Deep Reinforcement Learning Framework for Intraday Trading with Micro-level Market Embedding
However, it is hard to apply existing RL methods to intraday trading due to the following three limitations: 1) overlooking micro-level market information (e. g., limit order book); 2) only focusing on local price fluctuation and failing to capture the overall trend of the whole trading day; 3) neglecting the impact of market risk.
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).
Multi-agent Reinforcement Learning
reinforcement-learning
+2
Online Ad Hoc Teamwork under Partial Observability
Autonomous agents often need to work together as a team to accomplish complex cooperative tasks.
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.
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.
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.
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 (PL) learning is a typical weakly supervised classification problem, where a PL of an instance is a set of candidate labels such that a fixed but unknown candidate is the true label.
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).
Multi-agent Reinforcement Learning
reinforcement-learning
+2
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
+2
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.
Hierarchical Reinforcement Learning
Portfolio Optimization
+1
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.
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.
Efficient Reservoir Management through Deep Reinforcement Learning
Dams impact downstream river dynamics through flow regulation and disruption of upstream-downstream linkages.
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.
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.
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.
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 #6 on
Learning with noisy labels
on CIFAR-10N-Random1
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.
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.
Collaboration based Multi-Label Learning
It is well-known that exploiting label correlations is crucially important to multi-label learning.
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.
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.
