Demystifying Reproducibility in Meta- and Multi-Task Reinforcement Learning
暂无分享,去创建一个
Gaurav S. Sukhatme | Karol Hausman | Zhanpeng He | Chang Su | Ryan Julian | K. R. Zentner | Avnish Narayan | Tsan Kwong Wong | Yonghyun Cho | Keren Zhu | Linda Wong
[1] Marcin Andrychowicz,et al. Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Research , 2018, ArXiv.
[2] Sergey Levine,et al. QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation , 2018, CoRL.
[3] Amos J. Storkey,et al. How to train your MAML , 2018, ICLR.
[4] Marc G. Bellemare,et al. The Arcade Learning Environment: An Evaluation Platform for General Agents , 2012, J. Artif. Intell. Res..
[5] Eiko Yoneki,et al. RLgraph: Modular Computation Graphs for Deep Reinforcement Learning , 2019, MLSys.
[6] Li Zhang,et al. Learning to Learn: Meta-Critic Networks for Sample Efficient Learning , 2017, ArXiv.
[7] Marc G. Bellemare,et al. Dopamine: A Research Framework for Deep Reinforcement Learning , 2018, ArXiv.
[8] Karol Hausman,et al. Learning an Embedding Space for Transferable Robot Skills , 2018, ICLR.
[9] Silvio Savarese,et al. SURREAL: Open-Source Reinforcement Learning Framework and Robot Manipulation Benchmark , 2018, CoRL.
[10] Prabhat Nagarajan,et al. ChainerRL: A Deep Reinforcement Learning Library , 2019, ArXiv.
[11] Pierre-Yves Oudeyer,et al. How Many Random Seeds? Statistical Power Analysis in Deep Reinforcement Learning Experiments , 2018, ArXiv.
[12] Michael S. Bernstein,et al. ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.
[13] John Schulman,et al. Gotta Learn Fast: A New Benchmark for Generalization in RL , 2018, ArXiv.
[14] Fabien Moutarde,et al. Is Deep Reinforcement Learning Really Superhuman on Atari? , 2019, NeurIPS 2019.
[15] Samy Bengio,et al. Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML , 2020, ICLR.
[16] Oleksii Hrinchuk,et al. Catalyst.RL: A Distributed Framework for Reproducible RL Research , 2019, ArXiv.
[17] Philip Bachman,et al. Deep Reinforcement Learning that Matters , 2017, AAAI.
[18] Yoshua Bengio,et al. Torchmeta: A Meta-Learning library for PyTorch , 2019, ArXiv.
[19] Pierre-Yves Oudeyer,et al. A Hitchhiker's Guide to Statistical Comparisons of Reinforcement Learning Algorithms , 2019, RML@ICLR.
[20] Joelle Pineau,et al. Where Did My Optimum Go?: An Empirical Analysis of Gradient Descent Optimization in Policy Gradient Methods , 2018, ArXiv.
[21] Peter L. Bartlett,et al. RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning , 2016, ArXiv.
[22] Trevor Darrell,et al. Regularization Matters in Policy Optimization , 2019, ArXiv.
[23] Sergey Levine,et al. Trust Region Policy Optimization , 2015, ICML.
[24] Peter Stone,et al. Keepaway Soccer: From Machine Learning Testbed to Benchmark , 2005, RoboCup.
[25] Julian Togelius,et al. Obstacle Tower: A Generalization Challenge in Vision, Control, and Planning , 2019, IJCAI.
[26] Pieter Abbeel,et al. Benchmarking Model-Based Reinforcement Learning , 2019, ArXiv.
[27] John F. Canny,et al. Measuring the Reliability of Reinforcement Learning Algorithms , 2019, ICLR.
[28] Karol Hausman,et al. Gradient Surgery for Multi-Task Learning , 2020, NeurIPS.
[29] Sergey Levine,et al. Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning , 2019, CoRL.
[30] Katja Hofmann,et al. Meta Reinforcement Learning with Latent Variable Gaussian Processes , 2018, UAI.
[31] Tristan Deleu,et al. On the reproducibility of gradient-based Meta-Reinforcement Learning baselines , 2018 .
[32] Zeb Kurth-Nelson,et al. Learning to reinforcement learn , 2016, CogSci.
[33] Peter Henderson,et al. Reproducibility of Benchmarked Deep Reinforcement Learning Tasks for Continuous Control , 2017, ArXiv.
[34] John Schulman,et al. Leveraging Procedural Generation to Benchmark Reinforcement Learning , 2019, ICML.
[35] Tor Lattimore,et al. Behaviour Suite for Reinforcement Learning , 2019, ICLR.
[36] Sergey Levine,et al. High-Dimensional Continuous Control Using Generalized Advantage Estimation , 2015, ICLR.
[37] Germán Ros,et al. CARLA: An Open Urban Driving Simulator , 2017, CoRL.
[38] Joshua Achiam,et al. On First-Order Meta-Learning Algorithms , 2018, ArXiv.
[39] Pieter Abbeel,et al. Benchmarking Deep Reinforcement Learning for Continuous Control , 2016, ICML.
[40] Sergey Levine,et al. Meta-Reinforcement Learning of Structured Exploration Strategies , 2018, NeurIPS.
[41] Andrew J. Davison,et al. RLBench: The Robot Learning Benchmark & Learning Environment , 2019, IEEE Robotics and Automation Letters.
[42] Alex Graves,et al. Playing Atari with Deep Reinforcement Learning , 2013, ArXiv.
[43] Sergey Levine,et al. REPLAB: A Reproducible Low-Cost Arm Benchmark Platform for Robotic Learning , 2019, ArXiv.
[44] Pieter Abbeel,et al. Meta-Learning with Temporal Convolutions , 2017, ArXiv.
[45] Simon Brodeur,et al. HoME: a Household Multimodal Environment , 2017, ICLR.
[46] Salim Roukos,et al. Bleu: a Method for Automatic Evaluation of Machine Translation , 2002, ACL.
[47] Sergey Levine,et al. Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks , 2017, ICML.
[48] Joelle Pineau,et al. Natural Environment Benchmarks for Reinforcement Learning , 2018, ArXiv.
[49] Jakub W. Pachocki,et al. Dota 2 with Large Scale Deep Reinforcement Learning , 2019, ArXiv.
[50] Jing Peng,et al. Function Optimization using Connectionist Reinforcement Learning Algorithms , 1991 .
[51] James Bergstra,et al. Benchmarking Reinforcement Learning Algorithms on Real-World Robots , 2018, CoRL.
[52] David Silver,et al. Learning values across many orders of magnitude , 2016, NIPS.
[53] Peter Stone,et al. The Impact of Nondeterminism on Reproducibility in Deep Reinforcement Learning , 2018 .
[54] Sergey Levine,et al. Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection , 2016, Int. J. Robotics Res..
[55] Yee Whye Teh,et al. Distral: Robust multitask reinforcement learning , 2017, NIPS.
[56] Sergey Levine,et al. Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables , 2019, ICML.
[57] Gabriel Dulac-Arnold,et al. Challenges of Real-World Reinforcement Learning , 2019, ArXiv.
[58] Wojciech Jaskowski,et al. ViZDoom: A Doom-based AI research platform for visual reinforcement learning , 2016, 2016 IEEE Conference on Computational Intelligence and Games (CIG).
[59] Michael I. Jordan,et al. RLlib: Abstractions for Distributed Reinforcement Learning , 2017, ICML.
[60] Ali Farhadi,et al. AI2-THOR: An Interactive 3D Environment for Visual AI , 2017, ArXiv.
[61] Laura Graesser,et al. SLM Lab: A Comprehensive Benchmark and Modular Software Framework for Reproducible Deep Reinforcement Learning , 2019, ArXiv.
[62] Joelle Pineau,et al. RE-EVALUATE: Reproducibility in Evaluating Reinforcement Learning Algorithms , 2018 .
[63] Sebastian Thrun,et al. Explanation-based neural network learning a lifelong learning approach , 1995 .
[64] David Silver,et al. Meta-Gradient Reinforcement Learning , 2018, NeurIPS.
[65] Larry Rudolph,et al. Implementation Matters in Deep RL: A Case Study on PPO and TRPO , 2020, ICLR.