1
vote
Accepted
Doesn't the n-step Tree Backup algorithm negatively affect the DQN-Agent by creating inconsistent look-ahead targets?
Hence, I think we
would in general look only up to n-steps ahead rather than
always n-steps, since the n consecutive samples from the replay
buffer don't guarantee that the transitions happended ...
- 25.4k
1
vote
Accepted
How is $Q(s', a')$ calculated in SARSA and Q-Learning?
It seems that your problem is that you think that we must know the true value of $Q(s', a')$ in order to perform the SARSA update. This is not the case! SARSA is a reinforcement learning algorithm, ...
- 36.3k
Only top scored, non community-wiki answers of a minimum length are eligible
Related Tags
reinforcement-learning × 4bootstrapping × 4
q-learning × 1
deep-rl × 1
dqn × 1
monte-carlo-methods × 1
temporal-difference-methods × 1
experience-replay × 1
sarsa × 1
td-lambda × 1
stationary-policy × 1
lambda-return × 1
lambda-return-algorithm × 1