New answers tagged policies
1
vote
Accepted
Expected return formula for deterministic policy
Even for a deterministic policy ${\mu_\theta}$, its induced trajectory $\tau$ in RL still follows a distribution influenced under the said policy ${\mu_\theta}$ and there's usually a corresponding ...
Top 50 recent answers are included
Related Tags
policies × 81reinforcement-learning × 71
markov-decision-process × 15
value-functions × 14
off-policy-methods × 7
comparison × 6
q-learning × 6
policy-gradients × 6
deterministic-policy × 6
deep-rl × 5
terminology × 5
sutton-barto × 5
policy-iteration × 5
optimality × 5
dqn × 4
definitions × 4
proofs × 4
bellman-equations × 4
value-iteration × 4
optimal-policy × 4
math × 3
rewards × 3
environment × 3
importance-sampling × 3
stochastic-policy × 3