Index

A

action (action_manager.ActionManager attribute) action_equality (policy.Policy attribute) action_manager (module) action_space (greedy_gq.GreedyGQ attribute) (policy.Policy attribute) (wall_demo_example.GoForward attribute) (wall_demo_example.PavlovSoftmax attribute)

action_state_rep() (in module tools) ActionManager (class in action_manager) align_ir_example (module) alpha (greedy_gq.GreedyGQ attribute) (gtd.GTD attribute) (to_gtd.TOGTD attribute) AlternatingRotation (class in auto_docking_policies) auto_docking_policies (module)

B

base_state (action_manager.ActionManager attribute) beta (greedy_gq.GreedyGQ attribute) (gtd.GTD attribute) (to_gtd.TOGTD attribute) (wis_gtd.WISGTD attribute) (wis_to_gtd.WISTOGTD attribute)

C

calculate_return_example (module) CHANNELS (state_representation.StateConstants attribute) choose_action() (auto_docking_policies.Switch method) (policy.Policy method) COLLECT_DATA_FLAG (learning_foreground.LearningForeground attribute) compute_avg_td_error() (evaluator.Evaluator method)

compute_IS_ess() (evaluator.Evaluator method) compute_MSRE() (evaluator.Evaluator method) compute_return() (return_calculator.ReturnCalculator method) compute_rupee() (evaluator.Evaluator method) constant() (in module tools) create_state() (learning_foreground.LearningForeground method) (return_calculator.ReturnCalculator method)

D

decay() (in module tools) delta (gtd.GTD attribute) (to_gtd.TOGTD attribute) (wis_gtd.WISGTD attribute) (wis_to_gtd.WISTOGTD attribute)

dock_ir_parse() (in module tools)

E

e (gtd.GTD attribute) (to_gtd.TOGTD attribute) (wis_gtd.WISGTD attribute) (wis_to_gtd.WISTOGTD attribute) e_grad (to_gtd.TOGTD attribute) e_w (to_gtd.TOGTD attribute)

EGreedy (class in auto_docking_policies) equal_twists() (in module tools) Evaluator (class in evaluator) evaluator (module) exploiter (auto_docking_policies.Switch attribute) explorer (auto_docking_policies.Switch attribute)

F

feature_indices (policy.Policy attribute) (wall_demo_example.PavlovSoftmax attribute)

finished_episode (greedy_gq.GreedyGQ attribute) ForwardIfClear (class in auto_docking_policies) fwd_action_index (wall_demo_example.GoForward attribute)

G

get_next_pow2() (in module tools) get_observations() (state_representation.StateManager method) get_phi() (state_representation.StateManager method) get_probability() (auto_docking_policies.Switch method) (policy.Policy method) GoForward (class in wall_demo_example) GoForwardIfNotBump (class in calculate_return_example)

GoForwardWithRandomness (class in calculate_return_example) greedy_gq (module) GreedyGQ (class in greedy_gq) GTD (class in gtd) gtd (module) GVF (class in gvf) gvf (module)

I

IMAGE_CO (state_representation.StateConstants attribute) IMAGE_IHT_SIZE (state_representation.StateConstants attribute) IMAGE_LI (state_representation.StateConstants attribute) image_parse() (in module tools) IMAGE_START_INDEX (state_representation.StateConstants attribute)

IMU_IHT_SIZE (state_representation.StateConstants attribute) imu_parse() (in module tools) IMU_START_INDEX (state_representation.StateConstants attribute) indices_in_phi (state_representation.StateConstants attribute) IR_ITH_SIZE (state_representation.StateConstants attribute) IR_START_INDEX (state_representation.StateConstants attribute)

L

last_index (policy.Policy attribute) learning_foreground (module) LearningForeground (class in learning_foreground) lmbda (greedy_gq.GreedyGQ attribute) (gtd.GTD attribute) (to_gtd.TOGTD attribute) (wis_gtd.WISGTD attribute) (wis_to_gtd.WISTOGTD attribute)

N

Note (greedy_gq.GreedyGQ attribute) num_active_features (state_representation.StateConstants attribute) num_features (greedy_gq.GreedyGQ attribute) NUM_IMAGE_INTERVALS (state_representation.StateConstants attribute) NUM_IMAGE_TILINGS (state_representation.StateConstants attribute) NUM_IMU_TILES (state_representation.StateConstants attribute) NUM_IMU_TILINGS (state_representation.StateConstants attribute)

NUM_ODOM_TILES (state_representation.StateConstants attribute) NUM_ODOM_TILINGS (state_representation.StateConstants attribute) NUM_PP (state_representation.StateConstants attribute) NUM_PP_TILES (state_representation.StateConstants attribute) NUM_PP_TILINGS (state_representation.StateConstants attribute) NUM_RANDOM_POINTS (state_representation.StateConstants attribute) num_timesteps_explore (auto_docking_policies.Switch attribute)

O

ODOM_IHT_SIZE (state_representation.StateConstants attribute) ODOM_START_INDEX (state_representation.StateConstants attribute) old_gamma (gtd.GTD attribute) (to_gtd.TOGTD attribute) (wis_gtd.WISGTD attribute) (wis_to_gtd.WISTOGTD attribute)

old_rho (wis_to_gtd.WISTOGTD attribute) overrides() (in module tools)

P

pause_flag (action_manager.ActionManager attribute) PavlovSoftmax (class in wall_demo_example) pc2_parse() (in module tools) pi (policy.Policy attribute) PIXEL_FEATURE_LENGTH (state_representation.StateConstants attribute) Policy (class in policy) policy (module) PP_FEATURE_LENGTH (state_representation.StateConstants attribute)

PP_IHT_SIZE (state_representation.StateConstants attribute) PP_START_INDEX (state_representation.StateConstants attribute) predict() (greedy_gq.GreedyGQ method) (gtd.GTD method) (gvf.GVF method) (to_gtd.TOGTD method) (wis_gtd.WISGTD method) (wis_to_gtd.WISTOGTD method) publishers (learning_foreground.LearningForeground attribute)

R

read_source() (learning_foreground.LearningForeground method) recent (learning_foreground.LearningForeground attribute) return_calculator (module)

ReturnCalculator (class in return_calculator) run() (action_manager.ActionManager method) (learning_foreground.LearningForeground method) (return_calculator.ReturnCalculator method)

S

SCALE_IMU (state_representation.StateConstants attribute) SCALE_ODOM (state_representation.StateConstants attribute) SCALE_PP (state_representation.StateConstants attribute) SCALE_RGB (state_representation.StateConstants attribute) sensor_state_parse() (in module tools) set_pause_flag() (action_manager.ActionManager method) set_termination_flag() (action_manager.ActionManager method) softmax() (in module tools)

start_action_manager() (in module action_manager) start_learning_foreground() (in module learning_foreground) start_return_calculator() (in module return_calculator) state_representation (module) StateConstants (class in state_representation) StateManager (class in state_representation) stop_once (action_manager.ActionManager attribute) Switch (class in auto_docking_policies)

T

t (auto_docking_policies.Switch attribute) take_action() (learning_foreground.LearningForeground method) (return_calculator.ReturnCalculator method) td_error_prioritized_experience_replay() (greedy_gq.GreedyGQ method) tderr_elig (gtd.GTD attribute) (to_gtd.TOGTD attribute) (wis_gtd.WISGTD attribute) (wis_to_gtd.WISTOGTD attribute) termination_flag (action_manager.ActionManager attribute) theta (gtd.GTD attribute) (to_gtd.TOGTD attribute) (wis_gtd.WISGTD attribute) (wis_to_gtd.WISTOGTD attribute)

time_scale (wall_demo_example.PavlovSoftmax attribute) timing() (in module tools) to_gtd (module) to_replay_experience (learning_foreground.LearningForeground attribute) TOGTD (class in to_gtd) tools (module) topic_format (in module tools) TOTAL_FEATURE_LENGTH (state_representation.StateConstants attribute) TOTAL_IMAGE_FEATURE_LENGTH (state_representation.StateConstants attribute) TurnIfBump (class in calculate_return_example)

U

u (wis_gtd.WISGTD attribute) (wis_to_gtd.WISTOGTD attribute) uniform_experience_replay() (greedy_gq.GreedyGQ method) update() (auto_docking_policies.AlternatingRotation method) (auto_docking_policies.EGreedy method) (auto_docking_policies.ForwardIfClear method) (auto_docking_policies.Switch method) (calculate_return_example.GoForwardIfNotBump method) (calculate_return_example.GoForwardWithRandomness method) (calculate_return_example.TurnIfBump method) (evaluator.Evaluator method) (greedy_gq.GreedyGQ method) (gtd.GTD method) (gvf.GVF method) (policy.Policy method) (to_gtd.TOGTD method) (wall_demo_example.GoForward method) (wall_demo_example.PavlovSoftmax method) (wis_gtd.WISGTD method) (wis_to_gtd.WISTOGTD method)

update_action() (action_manager.ActionManager method) update_base_state() (action_manager.ActionManager method) update_colours() (visualize_pixels.Visualize method) update_gvfs() (learning_foreground.LearningForeground method) update_image() (visualize_pixels.Visualize method) update_return_buffers() (return_calculator.ReturnCalculator method)

V

v (wis_gtd.WISGTD attribute) (wis_to_gtd.WISTOGTD attribute) value_function (policy.Policy attribute) (wall_demo_example.PavlovSoftmax attribute)

vis (learning_foreground.LearningForeground attribute) Visualize (class in visualize_pixels) visualize_pixels (module)

W

w (gtd.GTD attribute) (to_gtd.TOGTD attribute) (wis_gtd.WISGTD attribute) (wis_to_gtd.WISTOGTD attribute)

wall_demo_example (module) wis_gtd (module) wis_to_gtd (module) WISGTD (class in wis_gtd) WISTOGTD (class in wis_to_gtd)