Imagined Value Gradients: Model-Based Policy Optimization with Transferable Latent Dynamics Models

Conference on Robot Learning (CoRL), 2019

9 October 2019

Arunkumar Byravan

Jost Tobias Springenberg

Martin Riedmiller

Papers citing "Imagined Value Gradients: Model-Based Policy Optimization with Transferable Latent Dynamics Models"

33 / 33 papers shown

Title
First Order Model-Based RL through Decoupled Backpropagation Joseph Amigo Rooholla Khorrambakht Elliot Chane-Sane Nicolas Mansard Ludovic Righetti 130 0 0 29 Aug 2025
Evaluating World Models with LLM for Decision Making Chang Yang Xinrun Wang Junzhe Jiang Qinggang Zhang Yi-Ju Chang LLMAG ELM 332 10 0 13 Nov 2024
Meta-DT: Offline Meta-RL as Conditional Sequence Modeling with World Model DisentanglementNeural Information Processing Systems (NeurIPS), 2024 Zhi Wang Li Zhang Wenhao Wu Yuanheng Zhu Dongbin Zhao C. L. Philip Chen OffRL 216 15 0 15 Oct 2024
Adaptive Horizon Actor-Critic for Policy Learning in Contact-Rich Differentiable Simulation Ignat Georgiev K. Srinivasan Jie Xu Eric Heiden Animesh Garg 328 20 0 28 May 2024
Guided Cooperation in Hierarchical Reinforcement Learning via Model-based RolloutIEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2023 Haoran Wang Zeshen Tang Leya Yang Yaoru Sun Fang Wang Siyu Zhang Ye-Ting Chen 285 2 0 24 Sep 2023
Diminishing Return of Value Expansion Methods in Model-Based Reinforcement LearningInternational Conference on Learning Representations (ICLR), 2023 Daniel Palenicek M. Lutter João Carvalho Jan Peters 149 4 0 07 Mar 2023
Leveraging Jumpy Models for Planning and Fast Learning in Robotic Domains Jingwei Zhang Jost Tobias Springenberg Arunkumar Byravan Leonard Hasenclever A. Abdolmaleki Dushyant Rao N. Heess Martin Riedmiller 131 5 0 24 Feb 2023
Investigating the role of model-based learning in exploration and transferInternational Conference on Machine Learning (ICML), 2023 Jacob Walker Eszter Vértes Yazhe Li Gabriel Dulac-Arnold Ankesh Anand T. Weber Jessica B. Hamrick OffRL 171 8 0 08 Feb 2023
Learning General World Models in a Handful of Reward-Free DeploymentsNeural Information Processing Systems (NeurIPS), 2022 Yingchen Xu Jack Parker-Holder Aldo Pacchiano Philip J. Ball Oleh Rybkin Stephen J. Roberts Tim Rocktaschel Edward Grefenstette OffRL 227 11 0 23 Oct 2022
A model-based approach to meta-Reinforcement Learning: Transformers and tree searchThe European Symposium on Artificial Neural Networks (ESANN), 2022 Brieuc Pinon Jean-Charles Delvenne Raphaël Jungers OffRL 199 3 0 24 Aug 2022
A Survey on Model-based Reinforcement LearningScience China Information Sciences (Sci. China Inf. Sci.), 2022 Fan Luo Tian Xu Hang Lai Xiong-Hui Chen Weinan Zhang Yang Yu OffRL LRM 280 147 0 19 Jun 2022
DreamingV2: Reinforcement Learning with Discrete World Models without ReconstructionIEEE/RJS International Conference on Intelligent RObots and Systems (IROS), 2022 Masashi Okada T. Taniguchi 3DV OffRL 197 34 0 01 Mar 2022
GrASP: Gradient-Based Affordance Selection for Planning Vivek Veeriah Zeyu Zheng Richard L. Lewis Satinder Singh 153 4 0 08 Feb 2022
Tutorial on amortized optimization Brandon Amos OffRL 722 71 0 01 Feb 2022
Model-Value Inconsistency as a Signal for Epistemic Uncertainty Angelos Filos Eszter Vértes Zita Marinho Gregory Farquhar Diana Borsa A. Friesen Feryal M. P. Behbahani Tom Schaul André Barreto Simon Osindero 321 7 0 08 Dec 2021
Self-Consistent Models and ValuesNeural Information Processing Systems (NeurIPS), 2021 Roy Miles Kate Baumli Zita Marinho Angelos Filos Matteo Hessel Hado van Hasselt David Silver 193 8 0 25 Oct 2021
Evaluating model-based planning and planner amortization for continuous control Arunkumar Byravan Leonard Hasenclever Piotr Trochim M. Berk Mirza Alessandro Davide Ialongo ... Jost Tobias Springenberg A. Abdolmaleki N. Heess J. Merel Martin Riedmiller 141 17 0 07 Oct 2021
Learning Dynamics Models for Model Predictive Agents M. Lutter Leonard Hasenclever Arunkumar Byravan Gabriel Dulac-Arnold Piotr Trochim N. Heess J. Merel Yuval Tassa AI4CE 188 29 0 29 Sep 2021
Collect & Infer -- a fresh look at data-efficient Reinforcement LearningConference on Robot Learning (CoRL), 2021 Martin Riedmiller Jost Tobias Springenberg Agrim Gupta N. Heess OffRL 137 21 0 23 Aug 2021
MBRL-Lib: A Modular Library for Model-based Reinforcement Learning Luis Pineda Brandon Amos Amy Zhang Nathan Lambert Roberto Calandra OffRL 294 52 0 20 Apr 2021
Learning and Planning in Complex Action SpacesInternational Conference on Machine Learning (ICML), 2021 Thomas Hubert Julian Schrittwieser Ioannis Antonoglou M. Barekatain Simon Schmitt David Silver 196 89 0 13 Apr 2021
Muesli: Combining Improvements in Policy OptimizationInternational Conference on Machine Learning (ICML), 2021 Matteo Hessel Ivo Danihelka Fabio Viola A. Guez Simon Schmitt Laurent Sifre T. Weber David Silver H. V. Hasselt 207 67 0 13 Apr 2021
Latent Skill Planning for Exploration and TransferInternational Conference on Learning Representations (ICLR), 2020 Kevin Xie Homanga Bharadhwaj Danijar Hafner Animesh Garg Florian Shkurti 259 24 0 27 Nov 2020
On the role of planning in model-based deep reinforcement learning Jessica B. Hamrick A. Friesen Feryal M. P. Behbahani A. Guez Fabio Viola Sims Witherspoon Thomas W. Anthony Lars Buesing Petar Velickovic T. Weber OffRL 329 71 0 08 Nov 2020
Representation Matters: Improving Perception and Exploration for Robotics Markus Wulfmeier Arunkumar Byravan Tim Hertweck I. Higgins Ankush Gupta ... Malcolm Reynolds Denis Teplyashin Agrim Gupta Thomas Lampe Martin Riedmiller 255 19 0 03 Nov 2020
Bridging Imagination and Reality for Model-Based Deep Reinforcement Learning Guangxiang Zhu Minghao Zhang Honglak Lee Chongjie Zhang OffRL 262 20 0 23 Oct 2020
Iterative Amortized Policy OptimizationNeural Information Processing Systems (NeurIPS), 2020 Joseph Marino Alexandre Piché Alessandro Davide Ialongo Yisong Yue OffRL 217 23 0 20 Oct 2020
Local Search for Policy Iteration in Continuous Control Jost Tobias Springenberg N. Heess D. Mankowitz J. Merel Arunkumar Byravan ... Julian Schrittwieser Yuval Tassa J. Buchli Dan Belov Martin Riedmiller OffRL 110 15 0 12 Oct 2020
Mastering Atari with Discrete World ModelsInternational Conference on Learning Representations (ICLR), 2020 Danijar Hafner Timothy Lillicrap Mohammad Norouzi Jimmy Ba DRL 733 1,040 0 05 Oct 2020
On the model-based stochastic value gradient for continuous reinforcement learningConference on Learning for Dynamics & Control (L4DC), 2020 Brandon Amos Samuel Stanton Denis Yarats A. Wilson 309 76 0 28 Aug 2020
Goal-Aware Prediction: Learning to Model What MattersInternational Conference on Machine Learning (ICML), 2020 Suraj Nair Silvio Savarese Chelsea Finn 162 69 0 14 Jul 2020
Learning to Fly via Deep Model-Based Reinforcement Learning Philip Becker-Ehmck Maximilian Karl Jan Peters Patrick van der Smagt SSL 320 39 0 19 Mar 2020
Dream to Control: Learning Behaviors by Latent ImaginationInternational Conference on Learning Representations (ICLR), 2019 Danijar Hafner Timothy Lillicrap Jimmy Ba Mohammad Norouzi VLM 531 1,613 0 03 Dec 2019