Ignasi Clavera

Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinforcement Learning

Oct 26, 2020
Younggyo Seo, Kimin Lee, Ignasi Clavera, Thanard Kurutach, Jinwoo Shin, Pieter Abbeel

Figure 2 for Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinforcement Learning

Figure 3 for Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinforcement Learning

Figure 4 for Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinforcement Learning

* Accepted in NeurIPS2020. First two authors contributed equally, website: https://sites.google.com/view/trajectory-mcl code: https://github.com/younggyoseo/trajectory_mcl

Access Paper or Ask Questions

Mutual Information Maximization for Robust Plannable Representations

May 16, 2020
Yiming Ding, Ignasi Clavera, Pieter Abbeel

Figure 2 for Mutual Information Maximization for Robust Plannable Representations

* Accepted at NeurIPS 2019 Workshop on Robot Learning: Control and Interaction in the Real World

Access Paper or Ask Questions

Model-Augmented Actor-Critic: Backpropagating through Paths

May 16, 2020
Ignasi Clavera, Violet Fu, Pieter Abbeel

Figure 2 for Model-Augmented Actor-Critic: Backpropagating through Paths

Figure 3 for Model-Augmented Actor-Critic: Backpropagating through Paths

Figure 4 for Model-Augmented Actor-Critic: Backpropagating through Paths

* Accepted paper at ICLR 2020

Access Paper or Ask Questions

Asynchronous Methods for Model-Based Reinforcement Learning

Oct 28, 2019
Yunzhi Zhang, Ignasi Clavera, Boren Tsai, Pieter Abbeel

Figure 2 for Asynchronous Methods for Model-Based Reinforcement Learning

Figure 3 for Asynchronous Methods for Model-Based Reinforcement Learning

Figure 4 for Asynchronous Methods for Model-Based Reinforcement Learning

* 10 pages, CoRL 2019

Access Paper or Ask Questions

Benchmarking Model-Based Reinforcement Learning

Jul 03, 2019
Tingwu Wang, Xuchan Bao, Ignasi Clavera, Jerrick Hoang, Yeming Wen, Eric Langlois, Shunshi Zhang, Guodong Zhang, Pieter Abbeel, Jimmy Ba

Figure 2 for Benchmarking Model-Based Reinforcement Learning

Figure 3 for Benchmarking Model-Based Reinforcement Learning

Figure 4 for Benchmarking Model-Based Reinforcement Learning

* 8 main pages, 8 figures; 14 appendix pages, 25 figures

Access Paper or Ask Questions

Sub-policy Adaptation for Hierarchical Reinforcement Learning

Jun 13, 2019
Alexander C. Li, Carlos Florensa, Ignasi Clavera, Pieter Abbeel

Figure 2 for Sub-policy Adaptation for Hierarchical Reinforcement Learning

Figure 3 for Sub-policy Adaptation for Hierarchical Reinforcement Learning

Figure 4 for Sub-policy Adaptation for Hierarchical Reinforcement Learning

* Contributed talk at the Workshop on Multi-Task and Lifelong Reinforcement Learning at ICML 2019

Access Paper or Ask Questions

Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning

Feb 27, 2019
Anusha Nagabandi, Ignasi Clavera, Simin Liu, Ronald S. Fearing, Pieter Abbeel, Sergey Levine, Chelsea Finn

Figure 2 for Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning

Figure 3 for Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning

Figure 4 for Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning

* First 2 authors contributed equally. Website: https://sites.google.com/berkeley.edu/metaadaptivecontrol

Access Paper or Ask Questions

ProMP: Proximal Meta-Policy Search

Oct 17, 2018
Jonas Rothfuss, Dennis Lee, Ignasi Clavera, Tamim Asfour, Pieter Abbeel

Figure 2 for ProMP: Proximal Meta-Policy Search

Figure 3 for ProMP: Proximal Meta-Policy Search

* The first three authors contributed equally. The paper is under review for ICLR 2019

Access Paper or Ask Questions

Model-Ensemble Trust-Region Policy Optimization

Oct 05, 2018
Thanard Kurutach, Ignasi Clavera, Yan Duan, Aviv Tamar, Pieter Abbeel

Figure 2 for Model-Ensemble Trust-Region Policy Optimization

Figure 3 for Model-Ensemble Trust-Region Policy Optimization

Figure 4 for Model-Ensemble Trust-Region Policy Optimization

Access Paper or Ask Questions

Model-Based Reinforcement Learning via Meta-Policy Optimization

Sep 14, 2018
Ignasi Clavera, Jonas Rothfuss, John Schulman, Yasuhiro Fujita, Tamim Asfour, Pieter Abbeel

Figure 2 for Model-Based Reinforcement Learning via Meta-Policy Optimization

Figure 3 for Model-Based Reinforcement Learning via Meta-Policy Optimization

Figure 4 for Model-Based Reinforcement Learning via Meta-Policy Optimization

* First 2 authors contributed equally. Accepted for Conference on Robot Learning (CoRL)

Access Paper or Ask Questions

1

2

>>