TBA
Time | Program |
---|---|
8h55 – 9h00 | Opening |
9h00 – 9h25 |
Formula RL: Deep Reinforcement Learning for Autonomous Racing using Telemetry Data Adrian Remonda, Sarah Krebs, Eduardo Veas, Granit Luzhnica and Roman Kern |
9h25 – 9h50 |
Improving On-policy Learning with Statistical Reward Accumulation Yubin Deng, Ke Yu, Dahua Lin, Xiaoou Tang and Chen Change Loy |
9h50 – 10h15 |
Extending Sliding-step Importance Weighting from Supervised Learning to Reinforcement Learning Tian Tian and Richard Sutton |
10h15 – 10h30 |
Reinforcement Learning for Large and Variable Scale Problems using Improvement Based Rewards Abhik Ray, Richa Verma and Harshad Khadilkar |
10h30 – 11h00 | Coffee break |
11h00 – 11h25 |
AMBER: Adaptive Multi-Batch Experience Replay for Continuous Action Control Seungyul Han and Youngchul Sung |
11h25 – 11h50 |
Multi-Model based Actor-Critic Haoran Wei and Keith Decker |
11h50 – 12h40 |
Invited Speaker: Beyond Rewards Balaraman Ravindran |
12h40 – 14h00 | Lunch break |
14h00 – 14h25 |
Hierarchical Reinforcement Learning for Multi-agent MOBA Game Zhijian Zhang, Haozheng Li, Luo Zhang, Tianyin Zheng, Ting Zhang, Xiong Hao, Xiaoxin Chen, Min Chen, Fangxu Xiao and Wei Zhou |
14h25 – 14h50 |
Continuous Curriculum Learning for Reinforcement Learning - slides Andrea Bassich and Daniel Kudenko |
14h50 – 15h15 |
Learning Effective Subgoals with Multi-Task Hierarchical Reinforcement Learning Dagui Chen, Qi Yan, Shangqi Guo, Zhile Yang, Xin Su and Feng Chen |
15h15 – 15h30 |
Adaptive Selection of Auxiliary Tasks in UNREAL - slides Hidenori Itaya, Tsubasa Hirakawa, Takayoshi Yamashita and Hironobu Fujiyoshi |
15h30 – 16h00 | Coffee break |
16h00 – 16h50 |
Invited Speaker: Efficient Robot Skill Learning: Grounded Simulation Learning and Imitation Learning from Observation Peter Stone |
16h50 – 17h15 |
A framework of dual replay buffer: balancing forgetting and generalization in reinforcement learning - slides Linjing Zhang, Zongzhang Zhang, Zhiyuan Pan, Yingfeng Chen, Jiangcheng Zhu, Zhaorong Wang, Meng Wang and Changjie Fan |
17h15 – 17h40 |
SEERL: Sample Efficient Ensemble Reinforcement Learning Rohan Saphal, Balaraman Ravindran, Dheevatsa Mudigere, Sasikanth Avancha and Bharat Kaul |
17h40 - 17h45 | Closing |