firstbacksecondback
30 Results
|
Poster
|
Tue 17:00 |
The Importance of Pessimism in Fixed-Dataset Policy Optimization Jacob Buckman · Carles Gelada · Marc G Bellemare |
|
|
Poster
|
Wed 1:00 |
Acting in Delayed Environments with Non-Stationary Markov Policies Esther Derman · Gal Dalal · Shie Mannor |
|
|
Poster
|
Thu 17:00 |
Non-asymptotic Confidence Intervals of Off-policy Evaluation: Primal and Dual Bounds Yihao Feng · Ziyang Tang · Na Zhang · Qiang Liu |
|
|
Poster
|
Tue 17:00 |
Autoregressive Dynamics Models for Offline Policy Evaluation and Optimization Michael Zhang · Thomas Paine · Ofir Nachum · Cosmin Paduraru · George Tucker · ziyu wang · Mohammad Norouzi |
|
|
Poster
|
Wed 9:00 |
Benchmarks for Deep Off-Policy Evaluation Justin Fu · Mohammad Norouzi · Ofir Nachum · George Tucker · ziyu wang · Alexander Novikov · Sherry Yang · Michael Zhang · Yutian Chen · Aviral Kumar · Cosmin Paduraru · Sergey Levine · Thomas Paine |
|
|
Poster
|
Thu 9:00 |
Enforcing robust control guarantees within neural network policies Priya Donti · Melrose Roderick · Mahyar Fazlyab · Zico Kolter |
|
|
Poster
|
Wed 9:00 |
Differentiable Trust Region Layers for Deep Reinforcement Learning Fabian Otto · Philipp Becker · Vien A Ngo · Hanna Ziesche · Gerhard Neumann |
|
|
Poster
|
Mon 17:00 |
UPDeT: Universal Multi-agent RL via Policy Decoupling with Transformers Siyi Hu · Fengda Zhu · Xiaojun Chang · Xiaodan Liang |
|
|
Poster
|
Tue 9:00 |
Learning Value Functions in Deep Policy Gradients using Residual Variance Yannis Flet-Berliac · reda ouhamma · odalric-ambrym maillard · philippe preux |
|
|
Spotlight
|
Thu 3:25 |
UPDeT: Universal Multi-agent RL via Policy Decoupling with Transformers Siyi Hu · Fengda Zhu · Xiaojun Chang · Xiaodan Liang |
|
|
Poster
|
Thu 1:00 |
Representation Balancing Offline Model-based Reinforcement Learning Byung-Jun Lee · Jongmin Lee · Kee-Eung Kim |
|
|
Poster
|
Wed 17:00 |
Modelling Hierarchical Structure between Dialogue Policy and Natural Language Generator with Option Framework for Task-oriented Dialogue System Jianhong Wang · Yuan Zhang · Tae-Kyun Kim · Yunjie Gu |