NeurIPS 2021 Workshop DeepRL Submissions

Self-Imitation Learning from Demonstrations
Georgiy Pshikhachev, Dmitry Ivanov, Vladimir Egorov, Aleksei Shpilman
- 12 Oct 2021 (modified: 22 Oct 2023)
- Deep RL Workshop NeurIPS 2021
- Readers: Everyone
Understanding and Preventing Capacity Loss in Reinforcement Learning
Clare Lyle, Mark Rowland, Will Dabney
- 12 Oct 2021 (modified: 22 Oct 2023)
- Deep RL Workshop NeurIPS 2021
- Readers: Everyone
Variance-Seeking Meta-Exploration to Handle Out-of-Distribution Tasks
Yashvir Singh Grewal, Frits de Nijs, Sarah Goodwin
- 12 Oct 2021 (modified: 05 May 2023)
- Deep RL Workshop NeurIPS 2021
- Readers: Everyone
A Closer Look at Gradient Estimators with Reinforcement Learning as Inference
Jonathan Wilder Lavington, Michael Teng, Mark Schmidt, Frank Wood
- 12 Oct 2021 (modified: 05 May 2023)
- Deep RL Workshop NeurIPS 2021
- Readers: Everyone
From One Hand to Multiple Hands: Imitation Learning for Dexterous Manipulation from Single-Camera Teleoperation
Yuzhe Qin, Hao Su, Xiaolong Wang
- 12 Oct 2021 (modified: 22 Oct 2023)
- Deep RL Workshop NeurIPS 2021
- Readers: Everyone
Attention-based Partial Decoupling of Policy and Value for Generalization in Reinforcement Learning
Nasik Muhammad Nafi, Creighton Glasscock, William Hsu
- 12 Oct 2021 (modified: 05 May 2023)
- Deep RL Workshop NeurIPS 2021
- Readers: Everyone
Imitation Learning from Observations under Transition Model Disparity
Tanmay Gangwani, Yuan Zhou, Jian Peng
- 12 Oct 2021 (modified: 22 Oct 2023)
- Deep RL Workshop NeurIPS 2021
- Readers: Everyone
Vision-Guided Quadrupedal Locomotion in the Wild with Multi-Modal Delay Randomization
Chieko Sarah Imai, Minghao Zhang, Yuchen Zhang, Marcin Kierebiński, Ruihan Yang, Yuzhe Qin, Xiaolong Wang
- 12 Oct 2021 (modified: 22 Oct 2023)
- Deep RL Workshop NeurIPS 2021
- Readers: Everyone
Learning from demonstrations with SACR2: Soft Actor-Critic with Reward Relabeling
Jesús Bujalance Martín, Raphaël Chekroun, Fabien Moutarde
- 12 Oct 2021 (modified: 05 May 2023)
- Deep RL Workshop NeurIPS 2021
- Readers: Everyone
Plan Better Amid Conservatism: Offline Multi-Agent Reinforcement Learning with Actor Rectification
Ling Pan, Longbo Huang, Tengyu Ma, Huazhe Xu
- 12 Oct 2021 (modified: 05 May 2023)
- Deep RL Workshop NeurIPS 2021
- Readers: Everyone
Generalisation in Lifelong Reinforcement Learning through Logical Composition
Geraud Nangue Tasse, Steven James, Benjamin Rosman
- 12 Oct 2021 (modified: 05 May 2023)
- Deep RL Workshop NeurIPS 2021
- Readers: Everyone
DreamerPro: Reconstruction-Free Model-Based Reinforcement Learning with Prototypical Representations
Fei Deng, Ingook Jang, Sungjin Ahn
- 12 Oct 2021 (modified: 22 Oct 2023)
- Deep RL Workshop NeurIPS 2021
- Readers: Everyone
Temporal-Difference Value Estimation via Uncertainty-Guided Soft Updates
Litian Liang, Yaosheng Xu, Stephen Marcus McAleer, Dailin Hu, Alexander Ihler, Pieter Abbeel, Roy Fox
- 12 Oct 2021 (modified: 05 May 2023)
- Deep RL Workshop NeurIPS 2021
- Readers: Everyone
Improving Actor-Critic Reinforcement Learning via Hamiltonian Monte Carlo Method
Duo XU
- 12 Oct 2021 (modified: 05 May 2023)
- Deep RL Workshop NeurIPS 2021
- Readers: Everyone
Learning Vision-Guided Quadrupedal Locomotion End-to-End with Cross-Modal Transformers
Ruihan Yang, Minghao Zhang, Nicklas Hansen, Huazhe Xu, Xiaolong Wang
- 12 Oct 2021 (modified: 22 Oct 2023)
- Deep RL Workshop NeurIPS 2021
- Readers: Everyone
Look Closer: Bridging Egocentric and Third-Person Views with Transformers for Robotic Manipulation
Rishabh Jangir, Nicklas Hansen, Sambaran Ghosal, Mohit Jain, Xiaolong Wang
- 12 Oct 2021 (modified: 22 Oct 2023)
- Deep RL Workshop NeurIPS 2021
- Readers: Everyone
Learning Value Functions from Undirected State-only Experience
Matthew Chang, Arjun Gupta, Saurabh Gupta
- 12 Oct 2021 (modified: 22 Oct 2023)
- Deep RL Workshop NeurIPS 2021
- Readers: Everyone
Target Entropy Annealing for Discrete Soft Actor-Critic
Yaosheng Xu, Dailin Hu, Litian Liang, Stephen Marcus McAleer, Pieter Abbeel, Roy Fox
- 12 Oct 2021 (modified: 05 May 2023)
- Deep RL Workshop NeurIPS 2021
- Readers: Everyone
Learning Action Translator for Meta Reinforcement Learning on Sparse-Reward Tasks
Yijie Guo, Qiucheng Wu, Honglak Lee
- 12 Oct 2021 (modified: 05 May 2023)
- Deep RL Workshop NeurIPS 2021
- Readers: Everyone
Follow the Object: Curriculum Learning for Manipulation Tasks with Imagined Goals
Ozsel Kilinc, Giovanni Montana
- 12 Oct 2021 (modified: 05 May 2023)
- Deep RL Workshop NeurIPS 2021
- Readers: Everyone
The Reflective Explorer: Online Meta-Exploration from Offline Data in Realistic Robotic Tasks
Rafael Rafailov, Varun Kumar Vijay, Tianhe Yu, Avi Singh, Mariano Phielipp, Chelsea Finn
- 12 Oct 2021 (modified: 05 May 2023)
- Deep RL Workshop NeurIPS 2021
- Readers: Everyone
BLAST: Latent Dynamics Models from Bootstrapping
Keiran Paster, Lev E McKinney, Sheila A. McIlraith, Jimmy Ba
- 12 Oct 2021 (modified: 05 May 2023)
- Deep RL Workshop NeurIPS 2021
- Readers: Everyone
Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoning
Dhruv Shah, Peng Xu, Yao Lu, Ted Xiao, Alexander T Toshev, Sergey Levine, brian ichter
- 12 Oct 2021 (modified: 05 May 2023)
- Deep RL Workshop NeurIPS 2021
- Readers: Everyone
Count-Based Temperature Scheduling for Maximum Entropy Reinforcement Learning
Dailin Hu, Pieter Abbeel, Roy Fox
- 12 Oct 2021 (modified: 05 May 2023)
- Deep RL Workshop NeurIPS 2021
- Readers: Everyone
Data Sharing without Rewards in Multi-Task Offline Reinforcement Learning
Tianhe Yu, Aviral Kumar, Yevgen Chebotar, Chelsea Finn, Sergey Levine, Karol Hausman
- 12 Oct 2021 (modified: 05 May 2023)
- Deep RL Workshop NeurIPS 2021
- Readers: Everyone