GitHub - Riashat/Reinforcement_Learning_Demos: Demonstrations of Reinforcement Learning algorithms, as part of the COMP767 Reinforcement Learning course at McGill University

Name		Name	Last commit message	Last commit date
Latest commit History 4 Commits
Dynamic_Programming_Presentation_1		Dynamic_Programming_Presentation_1
Monte-Carlo Methods Presentation		Monte-Carlo Methods Presentation
Baseline_Advantage_Function_Off_Policy_MC.py		Baseline_Advantage_Function_Off_Policy_MC.py
Baseline_Arbitrary_Off_Policy_MC.py		Baseline_Arbitrary_Off_Policy_MC.py
COMP767_Presentation2_Riashat_Islam.pdf		COMP767_Presentation2_Riashat_Islam.pdf
COMP_767_Presentation_3_TD_Learning.pdf		COMP_767_Presentation_3_TD_Learning.pdf
Compare_SARSA_QLearning_DoubleQLearning.py		Compare_SARSA_QLearning_DoubleQLearning.py
Riashat_Islam_COMP767_Presentation_1_Dynamic_Programming.pdf		Riashat_Islam_COMP767_Presentation_1_Dynamic_Programming.pdf
double_q_learning_gridworld.py		double_q_learning_gridworld.py
mc_control_onPolicy.py		mc_control_onPolicy.py
mc_prediction.py		mc_prediction.py
n_Q_sigma_algorithm.py		n_Q_sigma_algorithm.py
n_step_tree_backup.py		n_step_tree_backup.py
off_policy_MC_Boltzmann_Policy.py		off_policy_MC_Boltzmann_Policy.py
off_policy_MC_Greedy_Behaviour_Policies.py		off_policy_MC_Greedy_Behaviour_Policies.py
off_policy_MC_Sigmoid_Behaviour_Policy.py		off_policy_MC_Sigmoid_Behaviour_Policy.py
off_policy_MC_With_One_Step_TD.py		off_policy_MC_With_One_Step_TD.py
off_policy_MC_random_off_policy.py		off_policy_MC_random_off_policy.py
q_learning_cliffworld.py		q_learning_cliffworld.py
sarsa_cliffworld.py		sarsa_cliffworld.py

Riashat/Reinforcement_Learning_Demos