Action Space
Discount Factor (Gamma)
Horizon
Markov Decision Process (MDP)
-
S
Reward and Return: discounted return and why future rewards are discounted by γ — OpenAI Spinning Up Art… 3 terms
-
-
-
I
Markov Decision Processes: finite-horizon and infinite-horizon value functions — MIT 6.390 notes Art… 1 term
-
-
D
Specification gaming: the flip side of AI ingenuity — Google DeepMind (reward misspecification) Art… 1 term
No terms or links match your search.