Sort by
Refine Your Search
-
Category
-
Employer
-
Field
-
results. ● Deploy the results developed in the first stage to linear value function estimation problems in reinforcement learning theory. Establish the foundations to generalize the results to non-linear
-
mandatory. · Personal Competences: We are seeking highly motivated, independent thinkers, who are well organised and willing to learn. Summary of conditions: Full time work (37,5h/week) Contract
Searches related to reinforcement learning
Enter an email to receive alerts for reinforcement-learning positions