A Concentration Bound for LSPE($\lambda$)
Chandak, Siddharth, Borkar, Vivek S., Dolhare, Harsh
–arXiv.org Artificial Intelligence
The popular LSPE($\lambda$) algorithm for policy evaluation is revisited to derive a concentration bound that gives high probability performance guarantees from some time on.
arXiv.org Artificial Intelligence
Nov-30-2022
- Country:
- North America > United States
- Asia
- Middle East > Jordan (0.04)
- India > Maharashtra
- Mumbai (0.04)
- Genre:
- Research Report (0.50)
- Technology: