项目作者: upb-lea

项目描述 :
Lecture notes, tutorial tasks including solutions as well as online videos for the reinforcement learning course hosted by Paderborn University
高级语言: Jupyter Notebook
项目地址: git://github.com/upb-lea/reinforcement_learning_course_materials.git
创建时间: 2020-07-20T08:28:39Z
项目社区:https://github.com/upb-lea/reinforcement_learning_course_materials

开源协议:MIT License

下载


Algo_Compare_1650870688171.pdf
DDPG_1650870688245.pdf
DDPG_Overestimation_1650870688347.pdf
Policy_Update_Frequency_TD3_1650870688392.pdf
RL_Categories_1650870688455.pdf
TRPO_Style_Updates_1650870688483.pdf
SLH_Benchmarks_1650870685975.pdf
Short_Corridor_Problem_1650870687172.pdf
Sarsa_Lambda_Mountain_Car_1650870684998.pdf
TD_lambda_vs_offline_lambda_1650870685058.pdf
Traces_Sarsa_Gridworld_1650870685369.pdf
Actor-Critic_1650870685430.pdf
Gaussian_Distri_1650870685531.pdf
Gaussian_Policy_Multivariate_1650870685567.pdf
Gradient_ascent_1650870685571.pdf
REINFORCE_short_corridor_1650870685700.pdf
REINFORCE_short_corridor_baseline_1650870685919.pdf
Average_Bootstrap_Example_1650870684187.pdf
Backward_View_1650870684319.pdf
Eglibility_Trace_Example_1650870684350.pdf
Forward_View_1650870684431.pdf
Lambda_Return_Backup_1650870684494.pdf
Lambda_Weighting_Series_1650870684594.pdf
Offline_Lamba_vs_n_step_TD_1650870684615.pdf
Offline_Online_Lambda_Returns_1650870684791.pdf
Redoing_Updates_1650870684898.pdf
Simple_LinearRegression_Example_1650870682998.pdf
random_search_1650870683040.pdf
DQN_1650870683055.pdf
DQN_Atari_Results_1650870683129.pdf
DQN_Network_Silver_1650870683159.pdf
Inv_pendulum_1650870683171.pdf
LSPI_Inv_Pendulum_1650870683216.pdf
Model_types_action_value_1650870683235.pdf
Mountain_Car_BS_1650870683335.pdf
Mountain_Car_BS_Learning_Rate_1650870683374.pdf
Mountain_Car_BS_early_performance_1650870683571.pdf
Mountain_Car_BS_n_step_comp_1650870683625.pdf
Online_LSPI_Pendulum_1650870683650.pdf
Sarsa_Brakeout_1650870683725.pdf
Sarsa_Seaquest_1650870683812.pdf
Tile_Coding_1650870683853.pdf
decision_tree_1650870681990.pdf
fe_example_1650870682081.pdf
fe_example2_1650870682133.pdf
kfold-cv_1650870682153.pdf
levels_of_opt_1650870682194.pdf
neuron_1650870682255.pdf
sgd_1650870682322.pdf
Gradient_descent_1650870682355.pdf
Non_differentiable_functions_1650870682673.pdf
Rastrigin_1650870682905.pdf
MLP_1650870680373.pdf
RNN_over_sequence_1650870681765.pdf
act_funcs_1650870681795.pdf
bias_variance_1650870681828.pdf
comp_logos_1650870681974.pdf
direct_indirect_RL_1650870680260.pdf
CNN_over_sequence_1650870680341.pdf
Heuristic_search_tree_1650870678945.pdf
MCTS_1650870679012.pdf
Markov_Decision_Process_1650870679030.pdf
Prior_Sweeping_Dyna_1650870679088.pdf
Rollout_1650870679151.pdf
Trajectory_sampling_1650870679277.pdf
Windy_Grid_World_Example_Q_Sigma_1650870678002.pdf
n_Step_TD_Random_Walk_1650870678084.pdf
n_step_Sarsa_Grid_World_Example_1650870678142.pdf
Backup_one_step_1650870678167.pdf
Dyna_1650870678727.pdf
Dyna_Q_Blocking_1650870678769.pdf
Dyna_Q_Shortcut_1650870678784.pdf
Dyna_Simple_Maze_1650870678812.pdf
Dyna_Simple_Maze_Updates_1650870678832.pdf
Expected_vs_sample_updates_example_1650870678888.pdf
Forest_Tree_TD0_MC_RMS_Prediction_Good_Init_200_eps_1650870677141.pdf
Forest_Tree_TD0_MC_RMS_Prediction_Zero_Init_500_eps_1650870677150.pdf
Forest_Tree_TD0_Prediction_1650870677166.pdf
Windy_Gridworld_1650870677223.pdf
3_step_tree_backup_1650870677650.pdf
Back_Up_Q_sigma_1650870677738.pdf
Back_Up_n_Step_Methods_1650870677763.pdf
Back_Up_n_Step_Sarsa_1650870677800.pdf
Compare_RL_Methods_Update_1650870677831.pdf
Random_Walk_19_States_1650870677904.pdf
Random_Walk_Example_Q_Sigma_1650870677977.pdf
MC_Black_Jack_1650870675810.pdf
MC_ES_Black_Jack_1650870676214.pdf
MC_GPI_1650870676229.pdf
Back_Up_Expected_Sarsa_1650870676376.pdf
Back_Up_Q_learning_1650870676420.pdf
Back_Up_Sarsa_1650870676456.pdf
Back_Up_TD_1650870676482.pdf
Batch_AB_Example_1650870676492.pdf
Cliff_Walking_1650870676618.pdf
Cliff_Walking_Extended_1650870676632.pdf
Compare_RL_Methods_Update_1650870676732.pdf
Double_Learning_Example_1650870676890.pdf
Driving_home_example_1650870676950.pdf
Importance_Sampling_Blackjack_1650870674552.pdf