New answers tagged sutton-barto
1
vote
Where is the problem: in batch TD(0) algorithm or in the code to solve AB problem in Sutton-Barto RL book?
Based upon your reference background of the given sample episodes in one batch, you need to average v_pr(2) since there're 8 cases then update your vector v with vector v_pr before next batch before ...
- 561
Top 50 recent answers are included
Related Tags
sutton-barto × 92reinforcement-learning × 90
value-functions × 12
off-policy-methods × 9
function-approximation × 8
temporal-difference-methods × 8
policy-gradients × 7
proofs × 7
monte-carlo-methods × 7
sarsa × 7
markov-decision-process × 6
rewards × 6
notation × 6
importance-sampling × 6
policies × 5
reinforce × 5
discount-factor × 5
comparison × 4
value-iteration × 4
multi-armed-bandits × 4
q-learning × 3
deep-rl × 3
definitions × 3
reward-functions × 3
return × 3