AI Agent - arXivDaily 专题

1901.07621 2019-10-07 cs.GT cs.AI cs.LG cs.MA 62%

Single Deep Counterfactual Regret Minimization

Eric Steinberger

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

Comments 4th version changes: fix minor notational errors; improve format; incorporate structural feedback from NeurIPS review; *RESULTS ARE UNCHANGED*

1909.01387 2019-09-05 cs.LG cs.AI 62%

Making Efficient Use of Demonstrations to Solve Hard Exploration Problems

Tom Le Paine, Caglar Gulcehre, Bobak Shahriari, Misha Denil, Matt Hoffman, Hubert Soyer, Richard Tanburn, Steven Kapturowski, Neil Rabinowitz, Duncan Williams, Gabriel Barth-Maron, Ziyu Wang, Nando de Freitas, Worlds Team

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

1908.05256 2019-08-15 cs.RO cs.AI cs.LG cs.SY eess.SY 62%

Continuous Control for High-Dimensional State Spaces: An Interactive Learning Approach

Rodrigo Pérez-Dattari, Carlos Celemin, Javier Ruiz-del-Solar, Jens Kober

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

Comments 7 pages, 8 figures, IEEE International Conference on Robotics and Automation (ICRA 2019)

1810.02274 2019-08-07 cs.LG cs.AI cs.CV cs.RO stat.ML 62%

Episodic Curiosity through Reachability

Nikolay Savinov, Anton Raichuk, Raphaël Marinier, Damien Vincent, Marc Pollefeys, Timothy Lillicrap, Sylvain Gelly

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

Comments Accepted to ICLR 2019. Code at https://github.com/google-research/episodic-curiosity/. Videos at https://sites.google.com/view/episodic-curiosity/

1907.00884 2019-07-02 cs.LG cs.AI stat.ML 62%

On mechanisms for transfer using landmark value functions in multi-task lifelong reinforcement learning

Nick Denis

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

Comments 12 pages, 7 figures

1906.04355 2019-06-12 cs.LG cs.AI stat.ML 62%

Learning Powerful Policies by Using Consistent Dynamics Model

Shagun Sodhani, Anirudh Goyal, Tristan Deleu, Yoshua Bengio, Sergey Levine, Jian Tang

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

Comments Accpted at RLDM 2019

1903.06164 2019-06-11 cs.LG cs.CL stat.ML 62%

Episodic Memory Reader: Learning What to Remember for Question Answering from Streaming Data

Moonsu Han, Minki Kang, Hyunwoo Jung, Sung Ju Hwang

专题命中记忆与上下文管理：agent(abstract)；分类 cs.CL、cs.LG

Comments 18 pages, 20 figures, 1 table

1903.03176 2019-06-10 cs.LG cs.AI 62%

MinAtar: An Atari-Inspired Testbed for Thorough and Reproducible Reinforcement Learning Experiments

Kenny Young, Tian Tian

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

1906.02457 2019-06-07 cs.LG cs.AI stat.ML 62%

Clustered Reinforcement Learning

Xiao Ma, Shen-Yi Zhao, Wu-Jun Li

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

Comments 16pages, 3 figures

1805.04514 2019-05-27 cs.LG cs.AI stat.ML 62%

Metatrace Actor-Critic: Online Step-size Tuning by Meta-gradient Descent for Reinforcement Learning Control

Kenny Young, Baoxiang Wang, Matthew E. Taylor

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

1905.09334 2019-05-24 cs.LG cs.AI stat.ML 62%

The Journey is the Reward: Unsupervised Learning of Influential Trajectories

Jonathan Binas, Sherjil Ozair, Yoshua Bengio

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

Comments ICML'19 ERL Workshop

1904.02435 2019-05-16 cs.LG cs.AI cs.NE 62%

Self-Adapting Goals Allow Transfer of Predictive Models to New Tasks

Kai Olav Ellefsen, Jim Torresen

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

Comments Accepted for publication in the proceedings of the 2019 Symposium of the Norwegian AI Society

1905.02662 2019-05-08 cs.NE cs.AI cs.LG 62%

Continual and Multi-task Reinforcement Learning With Shared Episodic Memory

Artyom Y. Sorokin, Mikhail S. Burtsev

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

Comments Presented at the Task-Agnostic Reinforcement Learning Workshop at ICLR 2019

1903.04110 2019-03-12 cs.LG cs.AI stat.ML 62%

Hybrid Reinforcement Learning with Expert State Sequences

Xiaoxiao Guo, Shiyu Chang, Mo Yu, Gerald Tesauro, Murray Campbell

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

Comments AAAI 2019; https://github.com/XiaoxiaoGuo/tensor4rl

1903.03094 2019-03-08 cs.CL cs.AI 62%

Learning to Speak and Act in a Fantasy Text Adventure Game

Jack Urbanek, Angela Fan, Siddharth Karamcheti, Saachi Jain, Samuel Humeau, Emily Dinan, Tim Rocktäschel, Douwe Kiela, Arthur Szlam, Jason Weston

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.CL

1806.11525 2019-03-08 cs.CL cs.LG 62%

Counting to Explore and Generalize in Text-based Games

Xingdi Yuan, Marc-Alexandre Côté, Alessandro Sordoni, Romain Laroche, Remi Tachet des Combes, Matthew Hausknecht, Adam Trischler

专题命中记忆与上下文管理：agent(abstract)；分类 cs.CL、cs.LG

1811.01483 2019-03-05 cs.LG cs.AI stat.ML 62%

Contingency-Aware Exploration in Reinforcement Learning

Jongwook Choi, Yijie Guo, Marcin Moczulski, Junhyuk Oh, Neal Wu, Mohammad Norouzi, Honglak Lee

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

Comments In ICLR 2019

1809.05922 2019-02-26 cs.LG cs.AI stat.ML 62%

Memory Efficient Experience Replay for Streaming Learning

Tyler L. Hayes, Nathan D. Cahill, Christopher Kanan

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

Comments To appear in the IEEE International Conference on Robotics and Automation (ICRA) 2019

1902.08349 2019-02-25 cs.LG cs.AI stat.ML 62%

Generative Memory for Lifelong Reinforcement Learning

Aswin Raghavan, Jesse Hostetler, Sek Chai

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

Comments Abstract NICE 2019 conference

1902.00719 2019-02-05 cs.LG cs.AI cs.HC stat.ML 62%

Learning User Preferences via Reinforcement Learning with Spatial Interface Valuing

Miguel Alonso

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

Comments Submitted to HCI International 2019 Parallel Session on Spatial Interaction for Universal Access

1808.09819 2019-01-25 cs.LG cs.AI stat.ML 62%

Approximate Exploration through State Abstraction

Adrien Ali Taïga, Aaron Courville, Marc G. Bellemare

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

1901.05856 2019-01-18 cs.LG cs.AI 62%

Amplifying the Imitation Effect for Reinforcement Learning of UCAV's Mission Execution

Gyeong Taek Lee, Chang Ouk Kim

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

Comments 9 pages

1812.03381 2018-12-11 cs.LG cs.AI cs.NE stat.ML 62%

Learning Montezuma's Revenge from a Single Demonstration

Tim Salimans, Richard Chen

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

Comments Deep RL Workshop, NeurIPS 2018

1812.01260 2018-12-05 cs.CL cs.AI 62%

Tartan: A retrieval-based socialbot powered by a dynamic finite-state machine architecture

George Larionov, Zachary Kaden, Hima Varsha Dureddy, Gabriel Bayomi T. Kalejaiye, Mihir Kale, Srividya Pranavi Potharaju, Ankit Parag Shah, Alexander I Rudnicky

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.CL

1802.04181 2018-10-30 cs.AI cs.LG stat.ML 62%

State Representation Learning for Control: An Overview

Timothée Lesort, Natalia Díaz-Rodríguez, Jean-François Goudou, David Filliat

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

1810.10654 2018-10-26 cs.RO cs.AI cs.LG 62%

Sample-Efficient Learning of Nonprehensile Manipulation Policies via Physics-Based Informed State Distributions

Lerrel Pinto, Aditya Mandalika, Brian Hou, Siddhartha Srinivasa

专题命中记忆与上下文管理：planning(abstract)；分类 cs.AI、cs.LG

1810.08163 2018-10-19 cs.LG cs.AI 62%

Fast deep reinforcement learning using online adjustments from the past

Steven Hansen, Pablo Sprechmann, Alexander Pritzel, André Barreto, Charles Blundell

专题命中记忆与上下文管理：planning(abstract)；分类 cs.AI、cs.LG

Comments Accepted at NIPS 2018

1810.07254 2018-10-18 cs.LG cs.AI cs.MA stat.ML 62%

The Concept of Criticality in Reinforcement Learning

Yitzhak Spielberg, Amos Azaria

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

1810.05533 2018-10-15 cs.LG cs.AI stat.ML 62%

Empowerment-driven Exploration using Mutual Information Estimation

Navneet Madhu Kumar

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

Comments Preprint. Under Development. arXiv admin note: text overlap with arXiv:1807.02078 by other authors

1803.05340 2018-10-15 quant-ph cond-mat.mes-hall cs.AI cs.LG stat.ML 62%

Measurement-based adaptation protocol with quantum reinforcement learning

F. Albarrán-Arriagada, J. C. Retamal, E. Solano, L. Lamata

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

Journal ref Phys. Rev. A 98, 042315 (2018)

1. 记忆与上下文管理 4753 篇

Single Deep Counterfactual Regret Minimization

Making Efficient Use of Demonstrations to Solve Hard Exploration Problems

Continuous Control for High-Dimensional State Spaces: An Interactive Learning Approach

Episodic Curiosity through Reachability

On mechanisms for transfer using landmark value functions in multi-task lifelong reinforcement learning

Learning Powerful Policies by Using Consistent Dynamics Model

Episodic Memory Reader: Learning What to Remember for Question Answering from Streaming Data

MinAtar: An Atari-Inspired Testbed for Thorough and Reproducible Reinforcement Learning Experiments

Clustered Reinforcement Learning

Metatrace Actor-Critic: Online Step-size Tuning by Meta-gradient Descent for Reinforcement Learning Control

The Journey is the Reward: Unsupervised Learning of Influential Trajectories

Self-Adapting Goals Allow Transfer of Predictive Models to New Tasks

Continual and Multi-task Reinforcement Learning With Shared Episodic Memory

Hybrid Reinforcement Learning with Expert State Sequences

Learning to Speak and Act in a Fantasy Text Adventure Game

Counting to Explore and Generalize in Text-based Games

Contingency-Aware Exploration in Reinforcement Learning

Memory Efficient Experience Replay for Streaming Learning

Generative Memory for Lifelong Reinforcement Learning

Learning User Preferences via Reinforcement Learning with Spatial Interface Valuing

Approximate Exploration through State Abstraction

Amplifying the Imitation Effect for Reinforcement Learning of UCAV's Mission Execution

Learning Montezuma's Revenge from a Single Demonstration

Tartan: A retrieval-based socialbot powered by a dynamic finite-state machine architecture

State Representation Learning for Control: An Overview

Sample-Efficient Learning of Nonprehensile Manipulation Policies via Physics-Based Informed State Distributions

Fast deep reinforcement learning using online adjustments from the past

The Concept of Criticality in Reinforcement Learning

Empowerment-driven Exploration using Mutual Information Estimation

Measurement-based adaptation protocol with quantum reinforcement learning