New answers tagged rewards
0
What you define as regret is the case of Stochastic MAB's i.e MAB's with a fixed distribution. First of all the idea of regret in an Online setting is the loss incurred compared to the best agent (NOTE: I have used the term best agent as it can have differeing strategies, resulting in different best agents, in general we deal with a static agent, i.e whose ...
Top 50 recent answers are included
Related Tags
rewards × 86reinforcement-learning × 83
markov-decision-process × 11
deep-rl × 9
return × 8
dqn × 7
reward-design × 7
reward-shaping × 7
q-learning × 6
policy-gradients × 6
deep-learning × 5
ai-design × 5
comparison × 4
papers × 4
reward-functions × 4
neural-networks × 3
machine-learning × 3
game-ai × 3
ddpg × 3
agi × 2
definitions × 2
actor-critic-methods × 2
open-ai × 2
value-functions × 2
environment × 2