<?xml version="1.0" encoding="UTF-8"?> <urlset xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.sitemaps.org/schemas/sitemap/0.9 http://www.sitemaps.org/schemas/sitemap/0.9/sitemap.xsd" xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"> <url> <loc>https://rafaelcunha2013.github.io/news/announcement_2/</loc> <lastmod>2022-05-12T19:59:00+00:00</lastmod> </url> <url> <loc>https://rafaelcunha2013.github.io/news/announcement_4/</loc> <lastmod>2023-04-01T19:59:00+00:00</lastmod> </url> <url> <loc>https://rafaelcunha2013.github.io/news/announcement_5/</loc> <lastmod>2025-02-25T19:59:00+00:00</lastmod> </url> <url> <loc>https://rafaelcunha2013.github.io/news/announcement_6/</loc> <lastmod>2025-04-01T19:59:00+00:00</lastmod> </url> <url> <loc>https://rafaelcunha2013.github.io/news/announcement_7md/</loc> <lastmod>2026-04-01T19:59:00+00:00</lastmod> </url> <url> <loc>https://rafaelcunha2013.github.io/news/announcement_8/</loc> <lastmod>2026-06-01T07:00:00+00:00</lastmod> </url> <url> <loc>https://rafaelcunha2013.github.io/blog/2022/displaying-external-posts-on-your-al-folio-blog/</loc> <lastmod>2022-04-23T23:20:09+00:00</lastmod> </url> <url> <loc>https://rafaelcunha2013.github.io/projects/1_MARL/</loc> <lastmod>2026-11-21T00:17:26+00:00</lastmod> </url> <url> <loc>https://rafaelcunha2013.github.io/projects/2_transfer_bias/</loc> <lastmod>2026-11-21T00:17:26+00:00</lastmod> </url> <url> <loc>https://rafaelcunha2013.github.io/projects/3_sf_mo/</loc> <lastmod>2026-11-21T00:17:26+00:00</lastmod> </url> <url> <loc>https://rafaelcunha2013.github.io/projects/4_marl_gpi_sf/</loc> <lastmod>2026-11-21T00:17:26+00:00</lastmod> </url> <url> <loc>https://rafaelcunha2013.github.io/projects/5_tl_sf_ma_pomdp/</loc> <lastmod>2026-11-21T00:17:26+00:00</lastmod> </url> <url> <loc>https://rafaelcunha2013.github.io/projects/6_task_agnostic_exploration/</loc> <lastmod>2026-11-21T00:17:26+00:00</lastmod> </url> <url> <loc>https://rafaelcunha2013.github.io/projects/7_RL_challenge/</loc> <lastmod>2026-11-21T00:17:26+00:00</lastmod> </url> <url> <loc>https://rafaelcunha2013.github.io/projects/8_xrl/</loc> <lastmod>2026-11-21T00:17:26+00:00</lastmod> </url> <url> <loc>https://rafaelcunha2013.github.io/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/action-preferences-with-baseline-effect-of-reward-above/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/action-value-methods-and-policies-probabilities-of-each/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/actor-critic-roles-of-actor-and-critic-td/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/baseline-and-advantage-function-td-error-as-advantage/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/baseline-in-reinforce-motivation-and-required-property/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/batch-mc-vs-batch-td-0-with-real/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/batch-monte-carlo-versus-batch-td-0-value/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/bellman-equation-in-matrix-form-r-pi-and/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/bellman-equation-in-matrix-form-three-state-mdp/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/bellman-expectation-equations-derive-v-pi-s-pi/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/bellman-expectation-equations-numeric-check-at-a-gridworld/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/bellman-expectation-equations-numeric-check-at-the-gridworld/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/bellman-expectation-equations-prove-q-pi-from-v-2/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/bellman-expectation-equations-prove-q-pi-from-v/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/bellman-expectation-equations-q-pi-in-terms-of/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/bellman-optimality-operator-why-contraction-gives-convergence-of/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/cliff-walking-sarsa-q-learning-double-q-learning/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/conditional-probability-conditional-is-at-least-the-joint/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/conditional-probability-pass-versus-study-and-pass-conjunction/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/conditional-probability-prove-bayes-theorem/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/conditional-probability-random-moves-between-four-rooms/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/conditional-probability-ratio-of-conditionals-equals-ratio-of/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/cv/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/deadly-triad-and-dqn-instability-experience-replay-target/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/deep-q-networks-target-network-against-the-deadly/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/derivatives-four-elementary-derivatives/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/dp-vs-sampled-updates-model-free-counterparts-no/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/dyna-q-stochastic-and-changing-environments/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/dyna-q-vs-n-step-bootstrapping-in-the/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/dynamic-programming-solvers-design-an-mdp-matrix-form/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/epsilon-greedy-long-run-best-method-in-the/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/epsilon-greedy-probability-of-the-greedy-action-five/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/epsilon-greedy-probability-of-the-greedy-action-four/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/epsilon-greedy-probability-of-the-greedy-action-two/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/epsilon-greedy-time-steps-where-exploration-definitely-or/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/expected-sarsa-double-expected-sarsa-update-equations/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/expected-value-gradient-of-e-log-pi-x/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/expected-value-r-s-a-from-the-four-2/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/expected-value-r-s-a-from-the-four/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/expected-value-r-s-a-s-from-p/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/expected-value-return-of-policies-in-a-three/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/exploration-methods-deterministic-versus-stochastic-policies-hyperparameters-baseline/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/feature-vectors-motivation-vs-tabular-goal-of-feature/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/first-visit-and-every-visit-mc-values-of/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/function-approximation-when-tabular-methods-are-impractical/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/gradient-descent-learning-rate-reaching-the-minimum-in/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/gradient-descent-starting-points-stuck-at-a-saddle/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/gradient-descent-starting-points-that-end-in-a/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/gradients-counterexample-for-swapping-gradient-and-sum/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/gradients-simplify-five-expressions-with-expectations/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/gradients-true-or-false-on-six-identities/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/greedy-arm-selected-in-the-long-run-from/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/greedy-arm-selected-in-the-long-run-second/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/importance-sampling-off-policy-td-0-update-exercise/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/independence-the-two-definitions-are-equivalent/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/joint-pmf-marginals-conditional-and-independence/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/lambda-return-half-life-lambda-in-terms-of/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/law-of-total-probability-bulbs-from-two-factories/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/linear-function-approximation-design-two-features-for-grid/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/linear-to-deep-function-approximation-dqn-challenges-remedies/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/linear-vs-non-linear-function-approximators-trade-offs/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/markov-decision-process-modelling-a-warehouse-robot-markov/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/markov-decision-process-states-actions-rewards-for-traffic/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/markov-property-which-history-independence-equality-is-false/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/maximization-bias-when-overestimation-helps-bias-parameter-mu/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/maximization-bias-why-q-learning-overestimates-mitigation/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/maximization-bias-why-q-learning-overestimates/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/mc-td-0-and-td-lambda-prediction-implement/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/mc-vs-td-when-a-td-update-beats/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/monte-carlo-control-glie-behaviour-policy-conditions-for/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/monte-carlo-prediction-convergence-with-probability-1-via/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/monte-carlo-prediction-every-visit-versus-first-visit/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/n-step-td-why-a-19-state-random/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/news/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/off-policy-learning-identify-an-off-policy-scenario/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/on-policy-vs-off-policy-control-data-efficiency/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/on-policy-vs-off-policy-sarsa-vs-q/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/partial-derivatives-six-expressions-including-an-expectation/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/policy-based-rl-advantage-over-value-based-methods/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/policy-based-rl-family-for-continuous-action-spaces/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/policy-based-vs-value-based-rl-continuous-action/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/policy-evaluation-q-pi-and-an-added-state-2/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/policy-evaluation-q-pi-and-an-added-state/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/policy-gradient-theorem-on-policy-requirement-and-off/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/policy-gradient-theorem-unbiasedness-of-the-baseline-estimate/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/policy-improvement-theorem-proof-for-stochastic-policies/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/policy-iteration-and-value-iteration-implement-on-a/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/policy-iteration-epsilon-soft-policies-tie-breaking-action/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/policy-iteration-stochastic-policies-3-argument-p-and/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/policy-iteration-time-complexity-with-v-s-versus/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/probability-density-function-p-x-x-0-for/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/probability-density-function-show-the-uniform-density-is/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/probability-mass-functions-construct-and-verify-a-fair/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/probability-mass-functions-show-the-epsilon-greedy-policy/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/projects/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/publications/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/q-learning-find-and-fix-errors-in-faulty/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/q-learning-vs-sarsa-equivalence-under-greedy-action/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/q-learning-vs-sarsa-off-policy-vs-on/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/random-variables-are-rewards-discrete-continuous-or-mixed/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/random-variables-values-and-type-of-number-of/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/reinforce-actor-critic-and-ppo-inverted-pendulum-programming/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/reinforce-derivation-model-dependent-terms-and-model-free/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/reinforce-vs-value-based-action-spaces-exploration-variance/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/reinforce-with-baseline-unbiasedness-variance-exploration-principles/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/returns-and-discounting-g-1-with-0-5/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/returns-and-discounting-g-2-with-0-5/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/returns-and-discounting-maze-reward-design-discounted-and/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/returns-and-discounting-optimal-policy-of-a-two/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/returns-and-discounting-pole-balancing-episodic-vs-continuing/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-course-map/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-lectures/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-tutorials/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/sample-average-method-q-values-at-t-9/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/sarsa-derive-sampled-policy-evaluation-update-role-of/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/sarsa-find-and-fix-errors-in-faulty-pseudocode/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/sarsa-q-learning-numeric-update-of-q-s1/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/semi-gradient-sarsa-on-policy-vs-off-policy/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/semi-gradient-td-0-true-sgd-of-msve/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/sequences-convergence-and-limits-of-three-sequences/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/series-convergence-of-eight-sums-geometric-p-series/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/softmax-over-q-sarsa-vs-softmax-over-action/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/stochastic-policies-advantage-under-partial-observability-mcq/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/stochastic-policies-advantage-with-near-optimal-actions-mcq/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/stochastic-policies-perceptual-aliasing-policy-gradient-vs-q/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/supervision/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/tabular-methods-as-linear-function-approximation-with-one/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/td-0-first-episode-update-in-the-random/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/td-0-monte-carlo-error-as-a-sum/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/td-error-for-action-values-identity-g-t/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/td-target-as-estimate-of-v-or-q/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/temporal-difference-learning-why-td-estimates-are-biased/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/upper-confidence-bound-ucb-derive-the-uncertainty-term/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/value-functions-comparing-policies-by-v-pi-s/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/value-iteration-action-value-analogue-q-k-1/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/value-iteration-return-bound-convergence-stopping-rule-numeric/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/value-iteration-return-bound-error-bound-proof-stopping/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/value-iteration-update-rule-for-action-values-q/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/weighted-average-method-q-n-1-in-terms/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/weighted-average-method-q-values-at-t-9/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/weighted-average-method-step-size-from-the-target-2/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/weighted-average-method-step-size-from-the-target/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/blog/2022/</loc> </url> <url> <loc>https://rafaelcunha2013.github.io/proof-rondo/</loc> <lastmod>2026-11-21T00:16:50+00:00</lastmod> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/workspaces/ex-1-9-3.html</loc> <lastmod>2026-11-21T00:16:50+00:00</lastmod> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/workspaces/ex-2-6-2.html</loc> <lastmod>2026-11-21T00:16:50+00:00</lastmod> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/workspaces/ex-3-4-3.html</loc> <lastmod>2026-11-21T00:16:50+00:00</lastmod> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/workspaces/ex-3-4-4.html</loc> <lastmod>2026-11-21T00:16:50+00:00</lastmod> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/workspaces/ex-4-1-1.html</loc> <lastmod>2026-11-21T00:16:50+00:00</lastmod> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/workspaces/ex-4-5-2.html</loc> <lastmod>2026-11-21T00:16:50+00:00</lastmod> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/workspaces/ex-5-6-1-dqn.html</loc> <lastmod>2026-11-21T00:16:50+00:00</lastmod> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/workspaces/ex-5-6-1.html</loc> <lastmod>2026-11-21T00:16:50+00:00</lastmod> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/workspaces/ex-7-5-4.html</loc> <lastmod>2026-11-21T00:16:50+00:00</lastmod> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-exercises/workspaces/guide-mdp-class.html</loc> <lastmod>2026-11-21T00:16:50+00:00</lastmod> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-lectures/lecture-01/</loc> <lastmod>2026-11-21T00:16:50+00:00</lastmod> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-lectures/lecture-02/</loc> <lastmod>2026-11-21T00:16:50+00:00</lastmod> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-lectures/lecture-03/</loc> <lastmod>2026-11-21T00:16:50+00:00</lastmod> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-lectures/lecture-04/</loc> <lastmod>2026-11-21T00:16:50+00:00</lastmod> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-lectures/lecture-05/</loc> <lastmod>2026-11-21T00:16:50+00:00</lastmod> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-lectures/lecture-06/</loc> <lastmod>2026-11-21T00:16:50+00:00</lastmod> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-lectures/lecture-07/</loc> <lastmod>2026-11-21T00:16:50+00:00</lastmod> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-lectures/lecture-08/</loc> <lastmod>2026-11-21T00:16:50+00:00</lastmod> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-tutorials/tutorial-01-solutions.html</loc> <lastmod>2026-11-21T00:16:50+00:00</lastmod> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-tutorials/tutorial-01.html</loc> <lastmod>2026-11-21T00:16:50+00:00</lastmod> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-tutorials/tutorial-02-solutions.html</loc> <lastmod>2026-11-21T00:16:50+00:00</lastmod> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-tutorials/tutorial-02.html</loc> <lastmod>2026-11-21T00:16:50+00:00</lastmod> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-tutorials/tutorial-03-solutions.html</loc> <lastmod>2026-11-21T00:16:50+00:00</lastmod> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-tutorials/tutorial-03.html</loc> <lastmod>2026-11-21T00:16:50+00:00</lastmod> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-tutorials/tutorial-04-solutions.html</loc> <lastmod>2026-11-21T00:16:50+00:00</lastmod> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-tutorials/tutorial-04.html</loc> <lastmod>2026-11-21T00:16:50+00:00</lastmod> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-tutorials/tutorial-05-solutions.html</loc> <lastmod>2026-11-21T00:16:50+00:00</lastmod> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-tutorials/tutorial-05.html</loc> <lastmod>2026-11-21T00:16:50+00:00</lastmod> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-tutorials/tutorial-06-solutions.html</loc> <lastmod>2026-11-21T00:16:50+00:00</lastmod> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-tutorials/tutorial-06.html</loc> <lastmod>2026-11-21T00:16:50+00:00</lastmod> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-tutorials/tutorial-07-solutions.html</loc> <lastmod>2026-11-21T00:16:50+00:00</lastmod> </url> <url> <loc>https://rafaelcunha2013.github.io/teaching/rl-tutorials/tutorial-07.html</loc> <lastmod>2026-11-21T00:16:50+00:00</lastmod> </url> </urlset>