Results 51 to 54 of about 236 (54)

Neural Temporal Difference and Q Learning Provably Converge to Global Optima

Mathematics of Operations Research
Qi Cai, Zhuoran Yang, Jason D Lee
exaly  

MR1288948 (95i:90103) Spencer, J. Randomization, derandomization and antirandomization: three games. Theoret. Comput. Sci. 131 (1994), no. 2, 415â 429. (Reviewer: Nicola Mattoscio RINFO ), 90D05 (90C40)

1994
openaire   +1 more source

Optimal impulsive control of piecewise deterministic Markov processes

Stochastics, 2016
exaly  

Optimality Models in Behavioral Biology

SIAM Review, 2001
exaly