Provably Efficient Reinforcement Learning with Aggregated States
Xiuwen Wang (CUHK-SZ)
Speaker: Xiuwen Wang
Title: Provably Efficient Reinforcement Learning with Aggregated States
Time: Aug 13 2pm-5pm
Reference:
Dong, S., Van Roy, B., & Zhou, Z. (2019). Provably efficient reinforcement learning with aggregated states. arXiv preprint arXiv:1912.06366.
Dong, S., Van Roy, B., & Zhou, Z. (2021). Simple Agent, Complex Environment: Efficient Reinforcement Learning with Agent State. arXiv preprint arXiv:2102.05261.