Index

A

action (Episode attribute) active_visualizers (GridWorldVisualizer attribute) add_obs() (ValueIteration method) add_visualizer() (GridWorldVisualizer method) (Visualizer method)

alpha (TDLearning attribute) append() (Episode method) (Summary method) average_episode_reward() (Summary method) average_reward() (Episode method) (Summary method)

B

beta (TDLearning attribute)

BOLTZMANN (TDLearning attribute)

C

clock (GridWorldVisualizer attribute) close_render() (GridWorld method) colors (GridWorldVisualizer attribute) CONSOLE (Visualizer attribute)

count (LinearScheduler attribute) COUNT_BASED (TDLearning attribute) count_map (Counter attribute) Counter (class in smartstart.algorithms.counter)

D

DENSITY (Visualizer attribute)

done (Episode attribute)

E

E_GREEDY (TDLearning attribute) EASY (GridWorld attribute) easy() (in module smartstart.environments.presets) end (LinearScheduler attribute) env (Counter attribute) (GridWorldVisualizer attribute) (ValueIteration attribute)

Environment (class in smartstart.environments.environment) Episode (class in smartstart.utilities.datacontainers) episodes (Summary attribute) epsilon (TDLearning attribute) exploration (TDLearning attribute) EXTREME (GridWorld attribute) extreme() (in module smartstart.environments.presets)

F

fps (GridWorldVisualizer attribute)

from_json() (smartstart.utilities.datacontainers.Episode class method) (smartstart.utilities.datacontainers.Summary class method)

G

gamma (TDLearning attribute) (ValueIteration attribute) generate() (smartstart.environments.gridworld.GridWorld class method) generate_gridworld() (in module smartstart.environments.generate_gridworld) generate_smartstart_object() (in module smartstart.smartexploration.smartexploration) get_action() (TDLearning method) (ValueIteration method) get_all_states() (GridWorld method) get_count() (Counter method) get_count_map() (Counter method) get_data_directory() (in module smartstart.utilities.utilities) get_density() (Counter method) get_density_map() (Counter method) get_grid() (GridWorld method) get_next_q_action() (QLearning method) (QLearningLambda method) (SARSA method) (SARSALambda method) (TDLearning method) (TDLearningLambda method)

get_q_map() (TDLearning method) get_q_value() (TDLearning method) get_q_values() (TDLearning method) get_T_R() (GridWorld method) get_transition() (ValueIteration method) get_value_map() (ValueIteration method) goal (ValueIteration attribute) grid (GridWorldVisualizer attribute) GridWorld (class in smartstart.environments.gridworld) GridWorldVisualizer (class in smartstart.environments.gridworldvisualizer)

H

HARD (GridWorld attribute)

hard() (in module smartstart.environments.presets)

I

IMPOSSIBRUUHHH (GridWorld attribute)

increment() (Counter method) init_q_value (TDLearning attribute)

L

lamb (TDLearningLambda attribute) LinearScheduler (class in smartstart.utilities.scheduler)

LIVE_AGENT (Visualizer attribute) load() (smartstart.utilities.datacontainers.Summary class method)

M

max_itr (ValueIteration attribute) max_steps (TDLearning attribute) mean_reward_episode() (in module smartstart.utilities.plot) mean_reward_std_episode() (in module smartstart.utilities.plot)

MEDIUM (GridWorld attribute) medium() (in module smartstart.environments.presets) messages (GridWorldVisualizer attribute) min_error (ValueIteration attribute) moving_average() (in module smartstart.utilities.numerical)

N

name (GridWorldVisualizer attribute) (Summary attribute)

NONE (TDLearning attribute) num_episodes (TDLearning attribute)

O

obs (Episode attribute) obs_tp1 (Episode attribute)

obses (ValueIteration attribute) optimize() (ValueIteration method)

P

plot_summary() (in module smartstart.utilities.plot)

possible_actions() (GridWorld method) process_task() (in module smartstart.utilities.experimenter)

Q

Q (TDLearning attribute)

QLearning (class in smartstart.algorithms.qlearning) QLearningLambda (class in smartstart.algorithms.qlearning)

R

R (ValueIteration attribute) render() (GridWorld method) (GridWorldVisualizer method) (Visualizer method) reset() (Environment method) (GridWorld method) (TDLearning method) (ValueIteration method)

reward (Episode attribute) run_experiment() (in module smartstart.utilities.experimenter)

S

sample() (LinearScheduler method) (Scheduler method) SARSA (class in smartstart.algorithms.sarsa) SARSALambda (class in smartstart.algorithms.sarsa) save() (Summary method) save_plot() (in module smartstart.utilities.plot) save_to_gcloud() (Summary method) scale (LinearScheduler attribute) Scheduler (class in smartstart.utilities.scheduler) screen (GridWorldVisualizer attribute) set_goal() (ValueIteration method) set_reward() (ValueIteration method) set_transition() (ValueIteration method) show_plot() (in module smartstart.utilities.plot) size (GridWorldVisualizer attribute) smartstart (module) smartstart.algorithms (module) smartstart.algorithms.counter (module) smartstart.algorithms.qlearning (module) smartstart.algorithms.sarsa (module) smartstart.algorithms.tdlearning (module) smartstart.algorithms.valueiteration (module)

smartstart.environments (module) smartstart.environments.environment (module) smartstart.environments.generate_gridworld (module) smartstart.environments.gridworld (module) smartstart.environments.gridworldvisualizer (module) smartstart.environments.presets (module) smartstart.smartexploration (module) smartstart.smartexploration.smartexploration (module) smartstart.utilities (module) smartstart.utilities.datacontainers (module) smartstart.utilities.experimenter (module) smartstart.utilities.numerical (module) smartstart.utilities.plot (module) smartstart.utilities.scheduler (module) smartstart.utilities.utilities (module) start (LinearScheduler attribute) step (LinearScheduler attribute) step() (Environment method) (GridWorld method) steps_episode() (in module smartstart.utilities.plot) (Summary method) Summary (class in smartstart.utilities.datacontainers)

T

T (ValueIteration attribute) take_step() (TDLearning method) TDLearning (class in smartstart.algorithms.tdlearning) TDLearningLambda (class in smartstart.algorithms.tdlearning) temp (TDLearning attribute) threshold_traces (TDLearningLambda attribute) to_json() (Episode method) (Summary method)

total (Counter attribute) total_episode_reward() (Summary method) total_reward() (Episode method) (Summary method) traces (TDLearningLambda attribute) train() (TDLearning method) (TDLearningLambda method)

U

UCB (TDLearning attribute)

update_q_value() (TDLearning method) (TDLearningLambda method)

V

V (ValueIteration attribute) VALUE_FUNCTION (Visualizer attribute)

ValueIteration (class in smartstart.algorithms.valueiteration) Visualizer (class in smartstart.environments.environment) visualizer (Environment attribute)