Login / Signup
James-Michael Leahy
ORCID
Publication Activity (10 Years)
Years Active: 2022-2023
Publications (10 Years): 3
Top Topics
Average Reward
Policy Gradient
Gradient Flow
Markov Decision Processes
Top Venues
CoRR
ICML
</>
Publications
</>
Bekzhan Kerimkulov
,
James-Michael Leahy
,
David Siska
,
Lukasz Szpruch
,
Yufei Zhang
A Fisher-Rao gradient flow for entropy-regularised Markov decision processes in Polish spaces.
CoRR
(2023)
James-Michael Leahy
,
Bekzhan Kerimkulov
,
David Siska
,
Lukasz Szpruch
Convergence of Policy Gradient for Entropy Regularized MDPs with Neural Network Approximation in the Mean-Field Regime.
ICML
(2022)
Bekzhan Kerimkulov
,
James-Michael Leahy
,
David Siska
,
Lukasz Szpruch
Convergence of policy gradient for entropy regularized MDPs with neural network approximation in the mean-field regime.
CoRR
(2022)