Why can we take the action $a$ from the next state $s'$ in the max part of the Q-learning update rule, if that action doesn't lead to any reward?
How can the importance sampling ratio be different than zero when the target policy is deterministic?
Can I add expert data to the replay buffer used by the DDPG algorithm in order to make it converge faster?
Why is $M_t$ (the emphasis) helping in correcting for the state distribution in the Emphatic TD algorithm?
Only top scored, non community-wiki answers of a minimum length are eligible