Index _ | A | B | C | D | E | F | G | I | L | M | N | P | R | S | T | U | W | X | Z _ __init__() (irlc.ex01.agent.Agent method) (irlc.ex02.dp_model.DPModel method) (irlc.ex03.control_cost.SymbolicQRCost method) (irlc.ex03.control_model.ControlModel method) (irlc.ex04.control_environment.ControlEnvironment method) (irlc.ex04.discrete_control_cost.DiscreteQRCost method) (irlc.ex04.discrete_control_model.DiscreteControlModel method) (irlc.ex08.bandits.BanditEnvironment method) (irlc.ex08.bandits.StationaryBandit method) (irlc.ex09.mdp.MDP method) (irlc.ex09.rl_agent.TabularAgent method) (irlc.ex09.rl_agent.TabularQ method) (irlc.ex11.feature_encoder.FeatureEncoder method) (irlc.ex11.feature_encoder.LinearQEncoder method) (irlc.ex13.buffer.BasicBuffer method) (irlc.pacman.gamestate.GameState method) A A() (irlc.ex02.dp_model.DPModel method) (irlc.ex09.mdp.MDP method) (irlc.pacman.gamestate.GameState method) action_labels (irlc.ex04.discrete_control_model.DiscreteControlModel attribute) action_size (irlc.ex03.control_model.ControlModel property) (irlc.ex04.discrete_control_model.DiscreteControlModel property) Agent (class in irlc.ex01.agent) B backward_pass() (in module irlc.ex07.ilqr) bandit_step() (irlc.ex08.bandits.BanditEnvironment method) (irlc.ex08.bandits.StationaryBandit method) BanditEnvironment (class in irlc.ex08.bandits) BasicBuffer (class in irlc.ex13.buffer) C c() (irlc.ex04.discrete_control_cost.DiscreteQRCost method) close() (irlc.ex04.control_environment.ControlEnvironment method) cN() (irlc.ex04.discrete_control_cost.DiscreteQRCost method) collocate() (in module irlc.ex05.direct) ControlEnvironment (class in irlc.ex04.control_environment) ControlModel (class in irlc.ex03.control_model) cost_of_trajectory() (in module irlc.ex07.ilqr) D d (irlc.ex11.feature_encoder.FeatureEncoder property) (irlc.ex11.feature_encoder.LinearQEncoder property) DiscreteControlModel (class in irlc.ex04.discrete_control_model) DiscreteQRCost (class in irlc.ex04.discrete_control_cost) discretization_method (irlc.ex04.discrete_control_model.DiscreteControlModel attribute) discretize() (irlc.ex03.control_cost.SymbolicQRCost method) DP_stochastic() (in module irlc.ex02.dp) DPModel (class in irlc.ex02.dp_model) DQNNetwork (class in irlc.ex13.dqn_network) E extra_stats() (irlc.ex01.agent.Agent method) F f() (irlc.ex02.dp_model.DPModel method) (irlc.ex03.control_model.ControlModel method) (irlc.ex04.discrete_control_model.DiscreteControlModel method) (irlc.pacman.gamestate.GameState method) f_jacobian() (irlc.ex04.discrete_control_model.DiscreteControlModel method) FeatureEncoder (class in irlc.ex11.feature_encoder) fit() (irlc.ex13.dqn_network.DQNNetwork method) forward_pass() (in module irlc.ex07.ilqr) G g() (irlc.ex02.dp_model.DPModel method) GameState (class in irlc.pacman.gamestate) get_derivatives() (in module irlc.ex07.ilqr) get_optimal_action() (irlc.ex09.rl_agent.TabularQ method) (irlc.ex11.feature_encoder.FeatureEncoder method) get_Qs() (irlc.ex09.rl_agent.TabularQ method) (irlc.ex11.feature_encoder.FeatureEncoder method) gN() (irlc.ex02.dp_model.DPModel method) goal_seeking_cost() (irlc.ex03.control_cost.SymbolicQRCost method) (irlc.ex04.discrete_control_cost.DiscreteQRCost method) goal_seeking_terminal_cost() (irlc.ex03.control_cost.SymbolicQRCost method) (irlc.ex04.discrete_control_cost.DiscreteQRCost method) I initial_state_distribution() (irlc.ex09.mdp.MDP method) interactive() (in module irlc.utils.player_wrapper) is_lost() (irlc.pacman.gamestate.GameState method) is_terminal() (irlc.ex09.mdp.MDP method) is_won() (irlc.pacman.gamestate.GameState method) L LinearQEncoder (class in irlc.ex11.feature_encoder) load() (irlc.ex13.buffer.BasicBuffer method) LQR() (in module irlc.ex06.dlqr) M MDP (class in irlc.ex09.mdp) N nonterminal_states (irlc.ex09.mdp.MDP property) P phi_u() (irlc.ex03.control_model.ControlModel method) phi_u_inv() (irlc.ex03.control_model.ControlModel method) phi_x() (irlc.ex03.control_model.ControlModel method) phi_x_inv() (irlc.ex03.control_model.ControlModel method) pi() (irlc.ex01.agent.Agent method) pi_eps() (irlc.ex09.rl_agent.TabularAgent method) player() (irlc.pacman.gamestate.GameState method) players() (irlc.pacman.gamestate.GameState method) plot_trajectory() (in module irlc.utils.irlc_plot) plotenv() (in module irlc) Psr() (irlc.ex09.mdp.MDP method) push() (irlc.ex13.buffer.BasicBuffer method) Pw() (irlc.ex02.dp_model.DPModel method) R render() (irlc.ex03.control_model.ControlModel method) (irlc.ex04.control_environment.ControlEnvironment method) reset() (irlc.ex04.control_environment.ControlEnvironment method) (irlc.ex08.bandits.BanditEnvironment method) (irlc.ex08.bandits.StationaryBandit method) S S() (irlc.ex02.dp_model.DPModel method) sample() (irlc.ex13.buffer.BasicBuffer method) save() (irlc.ex13.buffer.BasicBuffer method) simulate() (irlc.ex03.control_model.ControlModel method) state_size (irlc.ex03.control_model.ControlModel property) (irlc.ex04.discrete_control_model.DiscreteControlModel property) states (irlc.ex09.mdp.MDP property) StationaryBandit (class in irlc.ex08.bandits) step() (irlc.ex04.control_environment.ControlEnvironment method) (irlc.ex08.bandits.BanditEnvironment method) sym_c() (irlc.ex03.control_cost.SymbolicQRCost method) sym_cf() (irlc.ex03.control_cost.SymbolicQRCost method) sym_f() (irlc.ex03.control_model.ControlModel method) SymbolicQRCost (class in irlc.ex03.control_cost) T t0_bound() (irlc.ex03.control_model.ControlModel method) TabularAgent (class in irlc.ex09.rl_agent) TabularQ (class in irlc.ex09.rl_agent) tF_bound() (irlc.ex03.control_model.ControlModel method) to_dict() (irlc.ex09.rl_agent.TabularQ method) train() (in module irlc.ex01.agent) (irlc.ex01.agent.Agent method) trapezoid_interpolant() (in module irlc.ex05.direct) U u_bound() (irlc.ex03.control_model.ControlModel method) update_Phi() (irlc.ex13.dqn_network.DQNNetwork method) W w_rnd() (irlc.ex02.dp_model.DPModel method) X x() (irlc.ex11.feature_encoder.FeatureEncoder method) (irlc.ex11.feature_encoder.LinearQEncoder method) x0_bound() (irlc.ex03.control_model.ControlModel method) x_bound() (irlc.ex03.control_model.ControlModel method) xF_bound() (irlc.ex03.control_model.ControlModel method) Z zero() (irlc.ex03.control_cost.SymbolicQRCost class method) (irlc.ex04.discrete_control_cost.DiscreteQRCost class method)
