New answers tagged value-functions
3
votes
Can we also estimate $V_{\pi}$ with SARSA?
What you suggest will work, the main restriction is needing to know $\pi$ fully in order to perform the conversion.
If you know that you are going to be estimating $V_{\pi}$ from the start, and have a ...
1
vote
Accepted
How is policy iteration capable of improving on a deterministic policy?
These statements are not true for policy iteration and dynamic programming:
Since the policy is stochastic and the initial state is the same, we'll always take the same path and evaluate the same ...
Top 50 recent answers are included
Related Tags
value-functions × 89reinforcement-learning × 80
bellman-equations × 20
q-learning × 16
policies × 13
comparison × 12
markov-decision-process × 8
value-iteration × 8
policy-iteration × 7
optimal-policy × 7
return × 6
expectation × 6
deep-rl × 5
sutton-barto × 5
dqn × 4
proofs × 4
monte-carlo-methods × 4
temporal-difference-methods × 4
terminology × 3
math × 3
definitions × 3
policy-gradients × 3
function-approximation × 3
reward-functions × 3
notation × 3