can any one help

dzw, no, this is research group, we don't care about your homeworks

sorry

@justHeuristic, сделай что-нибудь со своим репо, чтобы случайные люди не набегали в чат

UNIVERSAL AGENT FOR DISENTANGLING ENVIRONMENTS AND TASKS
https://openreview.net/pdf?id=B1mvVm-C-

Action Branching Architectures for Deep Reinforcement Learning
https://arxiv.org/abs/1711.08946

Counterfactual Multi-Agent Policy Gradients - has been selected as the Outstanding Student Paper for AAAI-18
https://arxiv.org/abs/1705.08926

подскажите, есть что-то про решению np полных задач нейронками/drl?

@EvgeniyZh, см. https://arxiv.org/abs/1611.09940 и дальше по графу цитирований

спс

BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems
Belief Reward Shaping in Reinforcement Learning
Deep Reinforcement Learning for Unsupervised Video Summarization with DiversityRepresentativeness Reward
Deep Reinforcement Learning that Matters
Distributional Reinforcement Learning with Quantile Regression
Efficient Probabilistic Performance Bounds for Inverse Reinforcement Learning
Feature Engineering for Predictive Modeling using Reinforcement Learning
Large Scaled Relation Extraction with Reinforcement Learning
Learning Structured Representation for Text Classification via Reinforcement Learning
Learning to Extract Coherent Summary via Deep Reinforcement Learning
MathDQN: Solving Arithmetic Word Problems via Deep Reinforcement Learning
Multi-Step Reinforcement Learning: A Unifying Algorithm
OptionGAN: Learning Joint Reward-Policy Options using Generative Adversarial Inverse Reinforcement Learning
PAC Reinforcement Learning with an Imperfect Model
Personalizing a Dialogue System with Transfer Reinforcement Learning
Phase-Parametric Policies for Reinforcement Learning in Cyclic Environments
R^3: Reinforced Ranker-Reader for Open-Domain Question Answering
Rainbow: Combining Improvements in Deep Reinforcement Learning
Recurrent Attentional Reinforcement Learning for Multi-label Image Recognition
Reinforced Multi-label Image Classification by Exploring Curriculum
Reinforcement Learning for Relation Classification from Noisy Data
Reinforcement Learning in POMDPs with Memoryless Options and Option-Observation Initiation Sets
Safe Reinforcement Learning via Shielding
Safe Reinforcement Learning via Formal Methods: Toward Safe Control Through Proof and Learning
Teaching a Machine to Read Maps with Deep Reinforcement Learning
Toward Deep Reinforcement Learning without a Simulator: An Autonomous Steering Example
Deterministic Policy Optimization by Combining Pathwise and Score Function Estimators for Discrete Action Spaces
Diverse Exploration for Fast and Safe Policy Improvement
Expected Policy Gradients
Hierarchical Policy Search via Return-Weighted Density Estimation
Knowledge-Based Policies for Qualitative Decentralized POMDPs
Learning with Options that Terminate Off-Policy
Optimizing Interventions via Offline Policy Evaluation: Studies in Citizen Science
Privacy-Preserving Policy Iteration for Decentralized POMDPs
An Optimal Online Method of Selecting Source Policies for Reinforcement Learning
Deep Q-learning from Demonstrations

Статьи принятые на AAAI-18

да там огромный список

и препринтов еще нет для многих

Бесит такое

@ipaulo выгони этих индусов отсюда)

@justHeuristic сделай так пожалуйста, чтобы случайные люди не попадали в этот чат

Люди уже русский учить начали)

Вот выучат – тогда и поговорим

Они меньше вас нафлудили 😅