├── .gitattributes ├── MAL ├── 01 MA Centralized-Q │ ├── LFAEstimator.m │ ├── MAEnvironment.m │ ├── macq.m │ ├── maq_iterationCount.mat │ ├── maq_reward.mat │ └── weights.mat ├── 02 MA Hysteretic-Q │ ├── LFAEstimator.m │ ├── MAEnvironment.m │ ├── a1_weights.mat │ ├── a2_weights.mat │ ├── mahq.m │ ├── maq_iterationCount.mat │ └── maq_reward.mat ├── 03 MAPG │ ├── MAEnvironment.m │ ├── PolicyEstimator.m │ ├── ValueEstimator.m │ ├── agent1_policy_weights.mat │ ├── agent2_policy_weights.mat │ ├── mapg.m │ ├── mapg_iterationCount.mat │ ├── mapg_reward.mat │ └── value_weights.mat └── Basic Functions │ ├── clcAngle.m │ ├── compare_fig.m │ ├── ds2nfu.m │ ├── make_epsilon_policy.m │ ├── make_greedy_policy.m │ ├── make_random_policy.m │ ├── q_value_or_policy2fig.m │ └── sigmoid.m ├── README.md ├── SAL ├── 01 DP │ ├── PE.m │ ├── PE_V.mat │ ├── PI.m │ ├── PI_P.mat │ ├── PI_P.svg │ ├── PI_V.mat │ ├── PI_simulationTime.mat │ ├── VI.m │ ├── VI_P.mat │ ├── VI_P.svg │ ├── VI_Q.mat │ ├── VI_Q.svg │ ├── VI_V.mat │ ├── VI_simulationTime.mat │ ├── Values.xlsx │ └── policy_evaluation.m ├── 02 MC │ ├── offpmc.m │ ├── offpmc_c.mat │ ├── offpmc_iterationCount.mat │ ├── offpmc_policy.mat │ ├── offpmc_q.mat │ ├── offpmc_reward.mat │ ├── onpmc.m │ ├── onpmc_iterationCount.mat │ ├── onpmc_policy.mat │ ├── onpmc_q.mat │ ├── onpmc_returns.mat │ └── onpmc_reward.mat ├── 03 TD │ ├── qLearning.m │ ├── qLearning_iterationCount.mat │ ├── qLearning_q.mat │ ├── qLearning_reward.mat │ ├── sarsa.m │ ├── sarsa_iterationCount.mat │ ├── sarsa_q.mat │ └── sarsa_reward.mat ├── 04 LFA │ ├── LFAEstimator.m │ ├── linear_function_approximation.m │ ├── onp_lfa_iterationCount.mat │ ├── onp_lfa_reward.mat │ └── onp_lfa_weights.mat ├── 05 DQN │ ├── DQN.m │ ├── DQNEstimator.m │ ├── DQN_iterationCount.mat │ ├── DQN_reward.mat │ ├── DQN_simulationTime.mat │ ├── DQN_weights.mat │ └── dqn_rwd.png ├── 06 LPG │ ├── PolicyEstimator.m │ ├── ValueEstimator.m │ ├── pg_iterationCount.mat │ ├── pg_reward.mat │ ├── policy_gradient.m │ ├── policy_weights.mat │ └── value_weights.mat ├── Basic Functions │ ├── ds2nfu.m │ ├── make_epsilon_policy.m │ ├── make_greedy_policy.m │ ├── make_random_policy.m │ ├── q_value_or_policy2fig.m │ └── sigmoid.m └── Environment │ ├── SAEnvironment.m │ └── clcAngle.m └── graduate_thesis.pdf /.gitattributes: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/.gitattributes -------------------------------------------------------------------------------- /MAL/01 MA Centralized-Q/LFAEstimator.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/MAL/01 MA Centralized-Q/LFAEstimator.m -------------------------------------------------------------------------------- /MAL/01 MA Centralized-Q/MAEnvironment.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/MAL/01 MA Centralized-Q/MAEnvironment.m -------------------------------------------------------------------------------- /MAL/01 MA Centralized-Q/macq.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/MAL/01 MA Centralized-Q/macq.m -------------------------------------------------------------------------------- /MAL/01 MA Centralized-Q/maq_iterationCount.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/MAL/01 MA Centralized-Q/maq_iterationCount.mat -------------------------------------------------------------------------------- /MAL/01 MA Centralized-Q/maq_reward.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/MAL/01 MA Centralized-Q/maq_reward.mat -------------------------------------------------------------------------------- /MAL/01 MA Centralized-Q/weights.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/MAL/01 MA Centralized-Q/weights.mat -------------------------------------------------------------------------------- /MAL/02 MA Hysteretic-Q/LFAEstimator.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/MAL/02 MA Hysteretic-Q/LFAEstimator.m -------------------------------------------------------------------------------- /MAL/02 MA Hysteretic-Q/MAEnvironment.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/MAL/02 MA Hysteretic-Q/MAEnvironment.m -------------------------------------------------------------------------------- /MAL/02 MA Hysteretic-Q/a1_weights.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/MAL/02 MA Hysteretic-Q/a1_weights.mat -------------------------------------------------------------------------------- /MAL/02 MA Hysteretic-Q/a2_weights.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/MAL/02 MA Hysteretic-Q/a2_weights.mat -------------------------------------------------------------------------------- /MAL/02 MA Hysteretic-Q/mahq.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/MAL/02 MA Hysteretic-Q/mahq.m -------------------------------------------------------------------------------- /MAL/02 MA Hysteretic-Q/maq_iterationCount.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/MAL/02 MA Hysteretic-Q/maq_iterationCount.mat -------------------------------------------------------------------------------- /MAL/02 MA Hysteretic-Q/maq_reward.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/MAL/02 MA Hysteretic-Q/maq_reward.mat -------------------------------------------------------------------------------- /MAL/03 MAPG/MAEnvironment.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/MAL/03 MAPG/MAEnvironment.m -------------------------------------------------------------------------------- /MAL/03 MAPG/PolicyEstimator.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/MAL/03 MAPG/PolicyEstimator.m -------------------------------------------------------------------------------- /MAL/03 MAPG/ValueEstimator.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/MAL/03 MAPG/ValueEstimator.m -------------------------------------------------------------------------------- /MAL/03 MAPG/agent1_policy_weights.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/MAL/03 MAPG/agent1_policy_weights.mat -------------------------------------------------------------------------------- /MAL/03 MAPG/agent2_policy_weights.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/MAL/03 MAPG/agent2_policy_weights.mat -------------------------------------------------------------------------------- /MAL/03 MAPG/mapg.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/MAL/03 MAPG/mapg.m -------------------------------------------------------------------------------- /MAL/03 MAPG/mapg_iterationCount.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/MAL/03 MAPG/mapg_iterationCount.mat -------------------------------------------------------------------------------- /MAL/03 MAPG/mapg_reward.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/MAL/03 MAPG/mapg_reward.mat -------------------------------------------------------------------------------- /MAL/03 MAPG/value_weights.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/MAL/03 MAPG/value_weights.mat -------------------------------------------------------------------------------- /MAL/Basic Functions/clcAngle.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/MAL/Basic Functions/clcAngle.m -------------------------------------------------------------------------------- /MAL/Basic Functions/compare_fig.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/MAL/Basic Functions/compare_fig.m -------------------------------------------------------------------------------- /MAL/Basic Functions/ds2nfu.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/MAL/Basic Functions/ds2nfu.m -------------------------------------------------------------------------------- /MAL/Basic Functions/make_epsilon_policy.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/MAL/Basic Functions/make_epsilon_policy.m -------------------------------------------------------------------------------- /MAL/Basic Functions/make_greedy_policy.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/MAL/Basic Functions/make_greedy_policy.m -------------------------------------------------------------------------------- /MAL/Basic Functions/make_random_policy.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/MAL/Basic Functions/make_random_policy.m -------------------------------------------------------------------------------- /MAL/Basic Functions/q_value_or_policy2fig.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/MAL/Basic Functions/q_value_or_policy2fig.m -------------------------------------------------------------------------------- /MAL/Basic Functions/sigmoid.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/MAL/Basic Functions/sigmoid.m -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/README.md -------------------------------------------------------------------------------- /SAL/01 DP/PE.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/01 DP/PE.m -------------------------------------------------------------------------------- /SAL/01 DP/PE_V.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/01 DP/PE_V.mat -------------------------------------------------------------------------------- /SAL/01 DP/PI.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/01 DP/PI.m -------------------------------------------------------------------------------- /SAL/01 DP/PI_P.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/01 DP/PI_P.mat -------------------------------------------------------------------------------- /SAL/01 DP/PI_P.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/01 DP/PI_P.svg -------------------------------------------------------------------------------- /SAL/01 DP/PI_V.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/01 DP/PI_V.mat -------------------------------------------------------------------------------- /SAL/01 DP/PI_simulationTime.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/01 DP/PI_simulationTime.mat -------------------------------------------------------------------------------- /SAL/01 DP/VI.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/01 DP/VI.m -------------------------------------------------------------------------------- /SAL/01 DP/VI_P.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/01 DP/VI_P.mat -------------------------------------------------------------------------------- /SAL/01 DP/VI_P.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/01 DP/VI_P.svg -------------------------------------------------------------------------------- /SAL/01 DP/VI_Q.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/01 DP/VI_Q.mat -------------------------------------------------------------------------------- /SAL/01 DP/VI_Q.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/01 DP/VI_Q.svg -------------------------------------------------------------------------------- /SAL/01 DP/VI_V.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/01 DP/VI_V.mat -------------------------------------------------------------------------------- /SAL/01 DP/VI_simulationTime.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/01 DP/VI_simulationTime.mat -------------------------------------------------------------------------------- /SAL/01 DP/Values.xlsx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/01 DP/Values.xlsx -------------------------------------------------------------------------------- /SAL/01 DP/policy_evaluation.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/01 DP/policy_evaluation.m -------------------------------------------------------------------------------- /SAL/02 MC/offpmc.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/02 MC/offpmc.m -------------------------------------------------------------------------------- /SAL/02 MC/offpmc_c.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/02 MC/offpmc_c.mat -------------------------------------------------------------------------------- /SAL/02 MC/offpmc_iterationCount.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/02 MC/offpmc_iterationCount.mat -------------------------------------------------------------------------------- /SAL/02 MC/offpmc_policy.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/02 MC/offpmc_policy.mat -------------------------------------------------------------------------------- /SAL/02 MC/offpmc_q.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/02 MC/offpmc_q.mat -------------------------------------------------------------------------------- /SAL/02 MC/offpmc_reward.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/02 MC/offpmc_reward.mat -------------------------------------------------------------------------------- /SAL/02 MC/onpmc.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/02 MC/onpmc.m -------------------------------------------------------------------------------- /SAL/02 MC/onpmc_iterationCount.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/02 MC/onpmc_iterationCount.mat -------------------------------------------------------------------------------- /SAL/02 MC/onpmc_policy.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/02 MC/onpmc_policy.mat -------------------------------------------------------------------------------- /SAL/02 MC/onpmc_q.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/02 MC/onpmc_q.mat -------------------------------------------------------------------------------- /SAL/02 MC/onpmc_returns.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/02 MC/onpmc_returns.mat -------------------------------------------------------------------------------- /SAL/02 MC/onpmc_reward.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/02 MC/onpmc_reward.mat -------------------------------------------------------------------------------- /SAL/03 TD/qLearning.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/03 TD/qLearning.m -------------------------------------------------------------------------------- /SAL/03 TD/qLearning_iterationCount.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/03 TD/qLearning_iterationCount.mat -------------------------------------------------------------------------------- /SAL/03 TD/qLearning_q.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/03 TD/qLearning_q.mat -------------------------------------------------------------------------------- /SAL/03 TD/qLearning_reward.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/03 TD/qLearning_reward.mat -------------------------------------------------------------------------------- /SAL/03 TD/sarsa.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/03 TD/sarsa.m -------------------------------------------------------------------------------- /SAL/03 TD/sarsa_iterationCount.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/03 TD/sarsa_iterationCount.mat -------------------------------------------------------------------------------- /SAL/03 TD/sarsa_q.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/03 TD/sarsa_q.mat -------------------------------------------------------------------------------- /SAL/03 TD/sarsa_reward.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/03 TD/sarsa_reward.mat -------------------------------------------------------------------------------- /SAL/04 LFA/LFAEstimator.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/04 LFA/LFAEstimator.m -------------------------------------------------------------------------------- /SAL/04 LFA/linear_function_approximation.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/04 LFA/linear_function_approximation.m -------------------------------------------------------------------------------- /SAL/04 LFA/onp_lfa_iterationCount.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/04 LFA/onp_lfa_iterationCount.mat -------------------------------------------------------------------------------- /SAL/04 LFA/onp_lfa_reward.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/04 LFA/onp_lfa_reward.mat -------------------------------------------------------------------------------- /SAL/04 LFA/onp_lfa_weights.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/04 LFA/onp_lfa_weights.mat -------------------------------------------------------------------------------- /SAL/05 DQN/DQN.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/05 DQN/DQN.m -------------------------------------------------------------------------------- /SAL/05 DQN/DQNEstimator.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/05 DQN/DQNEstimator.m -------------------------------------------------------------------------------- /SAL/05 DQN/DQN_iterationCount.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/05 DQN/DQN_iterationCount.mat -------------------------------------------------------------------------------- /SAL/05 DQN/DQN_reward.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/05 DQN/DQN_reward.mat -------------------------------------------------------------------------------- /SAL/05 DQN/DQN_simulationTime.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/05 DQN/DQN_simulationTime.mat -------------------------------------------------------------------------------- /SAL/05 DQN/DQN_weights.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/05 DQN/DQN_weights.mat -------------------------------------------------------------------------------- /SAL/05 DQN/dqn_rwd.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/05 DQN/dqn_rwd.png -------------------------------------------------------------------------------- /SAL/06 LPG/PolicyEstimator.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/06 LPG/PolicyEstimator.m -------------------------------------------------------------------------------- /SAL/06 LPG/ValueEstimator.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/06 LPG/ValueEstimator.m -------------------------------------------------------------------------------- /SAL/06 LPG/pg_iterationCount.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/06 LPG/pg_iterationCount.mat -------------------------------------------------------------------------------- /SAL/06 LPG/pg_reward.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/06 LPG/pg_reward.mat -------------------------------------------------------------------------------- /SAL/06 LPG/policy_gradient.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/06 LPG/policy_gradient.m -------------------------------------------------------------------------------- /SAL/06 LPG/policy_weights.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/06 LPG/policy_weights.mat -------------------------------------------------------------------------------- /SAL/06 LPG/value_weights.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/06 LPG/value_weights.mat -------------------------------------------------------------------------------- /SAL/Basic Functions/ds2nfu.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/Basic Functions/ds2nfu.m -------------------------------------------------------------------------------- /SAL/Basic Functions/make_epsilon_policy.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/Basic Functions/make_epsilon_policy.m -------------------------------------------------------------------------------- /SAL/Basic Functions/make_greedy_policy.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/Basic Functions/make_greedy_policy.m -------------------------------------------------------------------------------- /SAL/Basic Functions/make_random_policy.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/Basic Functions/make_random_policy.m -------------------------------------------------------------------------------- /SAL/Basic Functions/q_value_or_policy2fig.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/Basic Functions/q_value_or_policy2fig.m -------------------------------------------------------------------------------- /SAL/Basic Functions/sigmoid.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/Basic Functions/sigmoid.m -------------------------------------------------------------------------------- /SAL/Environment/SAEnvironment.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/Environment/SAEnvironment.m -------------------------------------------------------------------------------- /SAL/Environment/clcAngle.m: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/SAL/Environment/clcAngle.m -------------------------------------------------------------------------------- /graduate_thesis.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kunqian2025/reinforcement-learning/HEAD/graduate_thesis.pdf --------------------------------------------------------------------------------