Fingerprint
Dive into the research topics of 'Experiments with infinite-horizon, policy-gradient estimation'. Together they form a unique fingerprint.- Sort by
- Weight
- Alphabetically
Experiments with infinite-horizon, policy-gradient estimation
Jonathan Baxter*, Peter L. Bartlett, Lex Weaver
*Corresponding author for this work
Research output: Contribution to journal › Article › peer-review
114
Citations
(Scopus)