lrl
latest
General
Overview
Content
Installation Instructions
Acknowledgements and Contributions
Tutorials
Example Case using Racetrack
Boilerplate
Initialize an Environment
Solve with Value Iteration and Interrogate Solution
Plotting Results
Solving with Policy Iteration and Comparing to Value Iteration
Solve with Q-Learning
Example Case using RewardingFrozenLake
Boilerplate
Initialize an Environment
Solve with Value Iteration and Interrogate Solution
Plotting Results
Solving with Policy Iteration and Comparing to Value Iteration
Solve with Q-Learning
API
Solvers
Environments
Experiment Runners
Plotting
Data Stores
Miscellaneous Utilities
lrl
Docs
»
Index
Edit on GitHub
Index
_
|
A
|
B
|
C
|
D
|
E
|
G
|
I
|
K
|
L
|
N
|
P
|
Q
|
R
|
S
|
T
|
U
|
V
_
__getitem__() (lrl.data_stores.DictWithHistory method)
__setitem__() (lrl.data_stores.DictWithHistory method)
_policy_evaluation() (lrl.solvers.PolicyIteration method)
_policy_improvement() (lrl.solvers.PolicyIteration method)
(lrl.solvers.QLearning method)
A
add() (lrl.data_stores.EpisodeStatistics method)
(lrl.data_stores.GeneralIterationData method)
alpha() (lrl.solvers.QLearning property)
B
BaseSolver (class in lrl.solvers)
,
[1]
C
choose_epsilon_greedy_action() (lrl.solvers.QLearning method)
choose_text_size() (in module lrl.utils.plotting)
clear() (lrl.data_stores.DictWithHistory method)
close() (lrl.environments.Racetrack method)
color_map (lrl.environments.Racetrack attribute)
columns (lrl.data_stores.GeneralIterationData attribute)
compute() (lrl.data_stores.EpisodeStatistics method)
converged() (lrl.solvers.BaseSolver method)
,
[1]
(lrl.solvers.PolicyIteration method)
(lrl.solvers.QLearning method)
(lrl.solvers.ValueIteration method)
count_dict_differences() (in module lrl.utils.misc)
current_timepoint (lrl.data_stores.DictWithHistory attribute)
D
data (lrl.data_stores.GeneralIterationData attribute)
desc (lrl.environments.Racetrack attribute)
dict_differences() (in module lrl.utils.misc)
DictWithHistory (class in lrl.data_stores)
E
elapsed() (lrl.utils.misc.Timer method)
env (lrl.solvers.BaseSolver attribute)
,
[1]
episode_statistics (lrl.solvers.QLearning attribute)
episodes (lrl.data_stores.EpisodeStatistics attribute)
EpisodeStatistics (class in lrl.data_stores)
epsilon() (lrl.solvers.QLearning property)
G
GeneralIterationData (class in lrl.data_stores)
get() (lrl.data_stores.DictWithHistory method)
(lrl.data_stores.GeneralIterationData method)
get_ax() (in module lrl.utils.plotting)
get_q_at_state() (lrl.solvers.QLearning method)
get_statistic() (lrl.data_stores.EpisodeStatistics method)
get_statistics() (lrl.data_stores.EpisodeStatistics method)
get_value_at_timepoint() (lrl.data_stores.DictWithHistory method)
get_value_history() (lrl.data_stores.DictWithHistory method)
I
increment_timepoint() (lrl.data_stores.DictWithHistory method)
index_to_state (lrl.environments.Racetrack attribute)
init_policy() (lrl.solvers.BaseSolver method)
,
[1]
(lrl.solvers.PolicyIteration method)
(lrl.solvers.QLearning method)
(lrl.solvers.ValueIteration method)
init_q() (lrl.solvers.QLearning method)
is_location_terminal (lrl.environments.Racetrack attribute)
items() (lrl.data_stores.DictWithHistory method)
iterate() (lrl.solvers.BaseSolver method)
,
[1]
(lrl.solvers.PolicyIteration method)
(lrl.solvers.QLearning method)
(lrl.solvers.ValueIteration method)
iterate_to_convergence() (lrl.solvers.BaseSolver method)
,
[1]
(lrl.solvers.PolicyIteration method)
(lrl.solvers.QLearning method)
(lrl.solvers.ValueIteration method)
iteration_data (lrl.solvers.BaseSolver attribute)
,
[1]
(lrl.solvers.QLearning attribute)
K
keys() (lrl.data_stores.DictWithHistory method)
L
lrl.data_stores (module)
lrl.environments (module)
lrl.solvers (module)
lrl.utils.experiment_runners (module)
lrl.utils.misc (module)
lrl.utils.plotting (module)
N
num_episodes_for_convergence (lrl.solvers.QLearning attribute)
P
params_to_name() (in module lrl.utils.misc)
plot_env() (in module lrl.utils.plotting)
plot_episode() (in module lrl.utils.plotting)
plot_episodes() (in module lrl.utils.plotting)
plot_policy() (in module lrl.utils.plotting)
plot_solver_convergence() (in module lrl.utils.plotting)
plot_solver_convergence_from_df() (in module lrl.utils.plotting)
plot_solver_result() (in module lrl.utils.plotting)
plot_solver_results() (in module lrl.utils.plotting)
plot_value() (in module lrl.utils.plotting)
policy (lrl.solvers.BaseSolver attribute)
,
[1]
policy_dict_to_array() (in module lrl.utils.plotting)
PolicyIteration (class in lrl.solvers)
pop() (lrl.data_stores.DictWithHistory method)
popitem() (lrl.data_stores.DictWithHistory method)
print_dict_by_row() (in module lrl.utils.misc)
Q
q (lrl.solvers.QLearning attribute)
QLearning (class in lrl.solvers)
R
Racetrack (class in lrl.environments)
rc_to_xy() (in module lrl.utils.misc)
render() (lrl.environments.Racetrack method)
reset() (lrl.environments.Racetrack method)
rewards (lrl.data_stores.EpisodeStatistics attribute)
run_experiment() (in module lrl.utils.experiment_runners)
run_experiments() (in module lrl.utils.experiment_runners)
run_policy() (lrl.solvers.BaseSolver method)
,
[1]
(lrl.solvers.PolicyIteration method)
(lrl.solvers.QLearning method)
(lrl.solvers.ValueIteration method)
S
s (lrl.environments.Racetrack attribute)
score_policy() (lrl.solvers.BaseSolver method)
,
[1]
(lrl.solvers.PolicyIteration method)
(lrl.solvers.QLearning method)
(lrl.solvers.ValueIteration method)
scoring_episode_statistics (lrl.solvers.BaseSolver attribute)
,
[1]
scoring_summary (lrl.solvers.BaseSolver attribute)
,
[1]
seed() (lrl.environments.Racetrack method)
setdefault() (lrl.data_stores.DictWithHistory method)
start (lrl.utils.misc.Timer attribute)
state_to_index (lrl.environments.Racetrack attribute)
step() (lrl.environments.Racetrack method)
(lrl.solvers.QLearning method)
steps (lrl.data_stores.EpisodeStatistics attribute)
T
terminals (lrl.data_stores.EpisodeStatistics attribute)
timepoint_mode (lrl.data_stores.DictWithHistory attribute)
Timer (class in lrl.utils.misc)
to_csv() (lrl.data_stores.EpisodeStatistics method)
(lrl.data_stores.GeneralIterationData method)
to_dataframe() (lrl.data_stores.EpisodeStatistics method)
(lrl.data_stores.GeneralIterationData method)
to_dict() (lrl.data_stores.DictWithHistory method)
track (lrl.environments.Racetrack attribute)
transitions (lrl.solvers.QLearning attribute)
U
unwrapped() (lrl.environments.Racetrack property)
update() (lrl.data_stores.DictWithHistory method)
V
value (lrl.solvers.PolicyIteration attribute)
(lrl.solvers.ValueIteration attribute)
ValueIteration (class in lrl.solvers)
values() (lrl.data_stores.DictWithHistory method)
Read the Docs
v: latest
Versions
latest
Downloads
pdf
html
epub
On Read the Docs
Project Home
Builds
Free document hosting provided by
Read the Docs
.