| 000 -LEADER |
|---|
| fixed length control field |
01212nam a22001457a 4500 |
| 008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION |
|---|
| fixed length control field |
210710b ||||| |||| 00| 0 eng d |
| 100 ## - MAIN ENTRY--PERSONAL NAME |
|---|
| Personal name |
Damiano, Ettore and Li, Hao and Suen, Wing |
| 245 ## - TITLE STATEMENT |
|---|
| Title |
Learning while experimenting |
| 260 ## - PUBLICATION, DISTRIBUTION, ETC. (IMPRINT) |
|---|
| Place of publication, distribution, etc |
The Economic Journal: A Journal of the Royal Economic Society 1 |
| 300 ## - PHYSICAL DESCRIPTION |
|---|
| Extent |
30(625), Jan, 2020: p.65-92 |
| 520 ## - SUMMARY, ETC. |
|---|
| Summary, etc |
An agent performing risky experimentation can benefit from suspending it to learn directly about the state. ‘Positive’ information acquisition seeks news that would confirm the state that favours experimentation. It is used as a last-ditch effort when the agent is pessimistic about the risky arm before abandoning it. ‘Negative’ information acquisition seeks news that would demonstrate that experimentation is futile. It is used as an insurance strategy to avoid wasteful experimentation when the agent is still optimistic. A higher reward from risky experimentation expands the region of beliefs that the agent optimally chooses information acquisition rather than experimentation. – Reproduced |
| 773 ## - HOST ITEM ENTRY |
|---|
| Main entry heading |
The Economic Journal: A Journal of the Royal Economic Society |
| 906 ## - LOCAL DATA ELEMENT F, LDF (RLIN) |
|---|
| Subject DIP |
INFORMATION AND KNOWLEDGE |
| 942 ## - ADDED ENTRY ELEMENTS (KOHA) |
|---|
| Item type |
Articles |
