Tata Institute of Fundamental Research
Off-policy evaluation in Reinforcement Learning using Linear Regression
STCS Student Seminar
Speaker:
Anirban Bhattacharjee
Organiser:
Ashutosh Shankar
Date:
Friday, 11 Dec 2020, 17:15 to 18:15
Venue:
(Scan to add to calendar)
Abstract:
In Reinforcement Learning, one often needs to evaluate a given policy using rewards observed by following another policy. This is called off-policy evaluation in Learning Theory parlance. The traditional methods for off-policy evaluation involve importance sampling, which comes with certain drawbacks. We shall look at these drawbacks and how linear regression may be used instead to overcome the same.
Zoom link: https://zoom.us/j/98132227553?pwd=K2cyQllKVjExdUhlRm0vc0ZHcEt0Zz09
| Speaker: | Anirban Bhattacharjee |
| Organiser: | Ashutosh Shankar |
| Date: | Friday, 11 Dec 2020, 17:15 to 18:15 |
| Venue: |
(Scan to add to calendar)
Abstract:
In Reinforcement Learning, one often needs to evaluate a given policy using rewards observed by following another policy. This is called off-policy evaluation in Learning Theory parlance. The traditional methods for off-policy evaluation involve importance sampling, which comes with certain drawbacks. We shall look at these drawbacks and how linear regression may be used instead to overcome the same.
Zoom link: https://zoom.us/j/98132227553?pwd=K2cyQllKVjExdUhlRm0vc0ZHcEt0Zz09
Zoom link: https://zoom.us/j/98132227553?pwd=K2cyQllKVjExdUhlRm0vc0ZHcEt0Zz09