神経情報処理システム国際会議 NIPS

Conference on Advances in Neural Information Procession Systemsで発表された強化学習に関する論文．
（最近のものから順次追加しており，完全なリストではありません．）

採択率

• NIPS 2009: ?
• NIPS 2008: 250/1022=24.5%
• NIPS 2007: 217/975=22.3%

ロボット †

• Policy Search for Motor Primitives in Robotics
  Jens Kober, Jan Peters
  NIPS 2008, pp. 849-856 (2009).
• An Application of Reinforcement Learning to Aerobatic Helicopter Flight
  Pieter Abbeel, Adam Coates, Andrew Ng, Morgan Quigley
  NIPS 2006, pp. 1-8 (2007).

交通制御 †

• Natural Actor-Critic for Road Traffic Optimisation
  Silvia Richter, Douglas Aberdeen, Jin Yu
  NIPS 2006, pp. 1169-1176 (2007).

電力制御 †

• Managing Power Consumption and Performance of Computing Systems Using Reinforcement Learning
  Gerry Tesauro, Rajarshi Das, Hoi Chan, Jeffrey Kephart, David Levine, Freeman Rawson, Charles Lefurgy
  NIPS 2007, pp. 1497-1504 (2008).

見倣い学習 †

• Hierarchical Apprenticeship Learning with Application to Quadruped Locomotion
  J. Zico Kolter, Pieter Abbeel, Andrew Ng
  NIPS 2007, pp. 769-776 (2008).
• A Game-Theoretic Approach to Apprenticeship Learning
  Umar Syed, Robert Schapire
  NIPS 2007, pp. 1449-1456 (2008).

メタ学習 †

• Stress, noradrenaline, and realistic prediction of mouse behaviour using reinforcement learning
  Gediminas Lukšys, Carmen Sandi, Wulfram Gerstner
  NIPS 2008, pp. 1001-1008 (2009).
• Effects of Stress and Genotype on Meta-parameter Dynamics in Reinforcement Learning
  Gediminas Lukšys, Jérémie Knüsel, Denis Sheynikhovich, Carmen Sandi, Wulfram Gerstner
  NIPS 2006, pp. 937-944 (2007).

連続的行動空間 †

• Fitted Q-iteration by Advantage Weighted Regression
  Gerhard Neumann, Jan Peters
  NIPS 2008, pp. 1177-1184 (2009).
• Reinforcement Learning in Continuous Action Spaces through Sequential Monte Carlo Methods
  Alessandro Lazaric, Marcello Restelli, Andrea Bonarini
  NIPS 2007, pp. 833-840 (2008).
• Fitted Q-iteration in continuous action-space MDPs
  András Antos, Remi Munos, Csaba Szepesvari
  NIPS 2007, pp. 9-16 (2008).

探査と知識利用のジレンマ †

• Learning to Explore and Exploit in POMDPs
  Chenghui Cai, Xuejun Liao, Lawrence Carin
  NIPS 2009.

探査 †

• Multi-resolution Exploration in Continuous Spaces
  Ali Nouri, Michael Littman
  NIPS 2008, pp. 1209-1216 (2009).

学習分析 †

• Temporal Difference Updating without a Learning Rate
  Marcus Hutter, Shane Legg
  NIPS 2007, pp. 705-712 (2008).

勾配法 †

• Signal-to-Noise Ratio Analysis of Policy Gradient Algorithms
  John Roberts, Russ Tedrake
  NIPS 2008, pp. 1361-1368 (2009).
• Bayesian Policy Gradient Algorithms
  Mohammad Ghavamzadeh, Yaakov Engel
  NIPS 2006, pp. 457-464 (2007).

TD学習 †

• A Convergent O(n) Temporal-difference Algorithm for Off-policy Learning with Linear Function Approximation
  Rich Sutton, Csaba Szepesvari, Hamid Maei
  NIPS 2008, pp. 1609-1616 (2009).

アクター・クリティック †

• Temporal Difference Based Actor Critic Learning - Convergence and Neural Implementation
  Dotan Di Castro, Dima Volkinshtein, Ron Meir
  NIPS 2008, pp. 385-392 (2009).
• Incremental Natural Actor-Critic Algorithms
  Shalabh Bhatnagar, Rich Sutton, Mohammad Ghavamzadeh, Mark Lee
  NIPS 2007, pp. 105-112 (2008).

モデル・ベースド †

• Manifold Embeddings for Model-Based Reinforcement Learning under Partial Observability
  Keith Bush, Joelle Pineau
  NIPS 2009.
• Learning to Use Working Memory in Partially Observable Environments through Dopaminergic Reinforcement
  Michael Todd, Yael Niv, Jonathan Cohen
  NIPS 2008, pp. 1689-1696 (2009).

その他・未分類 †

• Training Factor Graphs with Reinforcement Learning for Efficient MAP Inference
  Michael Wick, Khashayar Rohanimanesh, Sameer Singh, Andrew McCallum
  NIPS 2009.
• Optimization on a Budget: A Reinforcement Learning Approach
  Paul Ruvolo, Ian Fasel, javier movellan
  NIPS 2008, pp. 1385-1392 (2009).
• Near-optimal Regret Bounds for Reinforcement Learning
  Peter Auer, Thomas Jaksch, Ronald Ortner
  NIPS 2008, pp. 89-96 (2009).
• Psychiatry: Insights into depression through normative decision-making models
  Quentin Huys, joshua vogelstein, Peter Dayan
  NIPS 2008, pp. 729-736 (2009).
• Logarithmic Online Regret Bounds for Undiscounted Reinforcement Learning
  Peter Auer, Ronald Ortner
  NIPS 2006, pp. 49-56 (2007).