| action_selector_type typedef | cuberl::rl::algos::td::DoubleQLearning< EnvTp, ActionSelector > | |
| action_type typedef | cuberl::rl::algos::td::DoubleQLearning< EnvTp, ActionSelector > | |
| actions_after_episode_ends(env_type &, uint_t episode_idx, const EpisodeInfo &) | cuberl::rl::algos::td::DoubleQLearning< EnvTp, ActionSelector > | inlinevirtual |
| TDAlgoBase< EnvTp >::actions_after_episode_ends(env_type &, uint_t, const EpisodeInfo &) | cuberl::rl::algos::RLSolverBase< EnvType > | inlinevirtual |
| actions_after_training_ends(env_type &) | cuberl::rl::algos::td::DoubleQLearning< EnvTp, ActionSelector > | virtual |
| TDAlgoBase< EnvTp >::actions_after_training_ends(env_type &)=0 | cuberl::rl::algos::RLSolverBase< EnvType > | pure virtual |
| actions_before_episode_begins(env_type &, uint_t) | cuberl::rl::algos::td::DoubleQLearning< EnvTp, ActionSelector > | inlinevirtual |
| TDAlgoBase< EnvTp >::actions_before_episode_begins(env_type &, uint_t) | cuberl::rl::algos::RLSolverBase< EnvType > | inlinevirtual |
| actions_before_training_begins(env_type &) | cuberl::rl::algos::td::DoubleQLearning< EnvTp, ActionSelector > | virtual |
| TDAlgoBase< EnvTp >::actions_before_training_begins(env_type &)=0 | cuberl::rl::algos::RLSolverBase< EnvType > | pure virtual |
| DoubleQLearning(const DoubleQLearningConfig config, const ActionSelector &selector) | cuberl::rl::algos::td::DoubleQLearning< EnvTp, ActionSelector > | |
| env_type typedef | cuberl::rl::algos::td::DoubleQLearning< EnvTp, ActionSelector > | |
| get(const state_type &state, const action_type action) const | cuberl::rl::with_double_q_table_mixin< DynMat< real_t > > | protected |
| get(const state_type &state, const action_type action) const | cuberl::rl::with_double_q_table_mixin< DynMat< real_t > > | protected |
| get(const state_type &state, const action_type action) const | cuberl::rl::with_double_q_table_mixin< DynMat< real_t > > | protected |
| index_type typedef | cuberl::rl::with_double_q_table_mixin< DynMat< real_t > > | protected |
| initialize(const std::vector< index_type > &indices, action_type n_actions, real_t init_value) | cuberl::rl::with_double_q_table_mixin< DynMat< real_t > > | protected |
| max_action(const TableTp &q1_table, const TableTp &q2_table, const StateTp &state, uint_t n_actions) | cuberl::rl::with_double_q_table_max_action_mixin | protectedstatic |
| max_action(const TableTp &q1_table, const StateTp &state, uint_t n_actions) | cuberl::rl::with_double_q_table_max_action_mixin | protectedstatic |
| on_training_episode(env_type &, uint_t episode_idx) | cuberl::rl::algos::td::DoubleQLearning< EnvTp, ActionSelector > | virtual |
| TDAlgoBase< EnvTp >::on_training_episode(env_type &, uint_t)=0 | cuberl::rl::algos::RLSolverBase< EnvType > | pure virtual |
| q_table_1 | cuberl::rl::with_double_q_table_mixin< DynMat< real_t > > | protected |
| q_table_2 | cuberl::rl::with_double_q_table_mixin< DynMat< real_t > > | protected |
| RLSolverBase()=default | cuberl::rl::algos::RLSolverBase< EnvType > | protected |
| save(std::string filename) const | cuberl::rl::algos::td::DoubleQLearning< EnvTp, ActionSelector > | |
| set(const state_type &state, const action_type action, const value_type value) | cuberl::rl::with_double_q_table_mixin< DynMat< real_t > > | protected |
| set(const state_type &state, const action_type action, const value_type value) | cuberl::rl::with_double_q_table_mixin< DynMat< real_t > > | protected |
| set(const state_type &state, const action_type action, const value_type value) | cuberl::rl::with_double_q_table_mixin< DynMat< real_t > > | protected |
| state_type typedef | cuberl::rl::algos::td::DoubleQLearning< EnvTp, ActionSelector > | |
| TDAlgoBase()=default | cuberl::rl::algos::td::TDAlgoBase< EnvTp > | protected |
| value_type typedef | cuberl::rl::with_double_q_table_mixin< DynMat< real_t > > | protected |
| ~RLSolverBase()=default | cuberl::rl::algos::RLSolverBase< EnvType > | virtual |
| ~TDAlgoBase()=default | cuberl::rl::algos::td::TDAlgoBase< EnvTp > | virtual |
1.9.8