Reinforcement learning via sequence modeling - Beyond Markovian assumption
Liangqi Liu (CUHK-SZ)
Speaker: Liangqi Liu
Title: Reinforcement learning via sequence modeling - Beyond Markovian assumption
Time: Jul 2 2pm-5pm
Reference:
Chen, L., Lu, K., Rajeswaran, A., Lee, K., Grover, A., Laskin, M., … & Mordatch, I. (2021). Decision transformer: Reinforcement learning via sequence modeling. arXiv preprint arXiv:2106.01345.
Janner, M., Li, Q., & Levine, S. (2021). Reinforcement Learning as One Big Sequence Modeling Problem. arXiv preprint arXiv:2106.02039.