liuzhiyug/moonrllab/examples/basic

README
Tr
Agent
Tr
Environment
Tr
Logger
Tr
Policy
- ::actionsBanditEnv::actions
- ::arm_countBanditEnv::arm_count
- ::average_rewardBanditEnv::average_reward
- ::best_armBanditEnv::best_arm
- ::newBanditEnv::new
- ::pull_countBanditEnv::pull_count
- ::renderBanditEnv::render
- ::resetBanditEnv::reset
- ::state_spaceBanditEnv::state_space
- ::stepBanditEnv::step
- ::chooseBanditPolicy::choose
- ::countsBanditPolicy::counts
- ::estimateBanditPolicy::estimate
- ::newBanditPolicy::new
- ::observeBanditPolicy::observe
- ::banditBenchmarkCase::bandit
- ::cliff_walkingBenchmarkCase::cliff_walking
- ::gridworldBenchmarkCase::gridworld
- ::random_walkBenchmarkCase::random_walk
- ::newBenchmarkResult::new
- ::recordBenchmarkResult::record
- ::reward_statsBenchmarkResult::reward_stats
- ::solve_rateBenchmarkResult::solve_rate
- ::solved_countBenchmarkResult::solved_count
- ::step_statsBenchmarkResult::step_stats
- ::summaryBenchmarkResult::summary
- ::tail_averageBenchmarkResult::tail_average
- ::to_csvBenchmarkResult::to_csv
- ::actionsCliffWalkingEnv::actions
- ::newCliffWalkingEnv::new
- ::renderCliffWalkingEnv::render
- ::resetCliffWalkingEnv::reset
- ::state_spaceCliffWalkingEnv::state_space
- ::stepCliffWalkingEnv::step
- ::newConsoleLogger::new
- ::best_actionDoubleQLearningAgent::best_action
- ::choose_actionDoubleQLearningAgent::choose_action
- ::learnDoubleQLearningAgent::learn
- ::newDoubleQLearningAgent::new
- ::update_countDoubleQLearningAgent::update_count
- ::valueDoubleQLearningAgent::value
- ::banditEnvironmentAudit::bandit
- ::cliffEnvironmentAudit::cliff
- ::gridworldEnvironmentAudit::gridworld
- ::random_walkEnvironmentAudit::random_walk
- ::finishEpisodeAccumulator::finish
- ::newEpisodeAccumulator::new
- ::observeEpisodeAccumulator::observe
T
EpisodeRecord
T
EpisodeStage
- ::lengthEpisodeTrace::length
- ::newEpisodeTrace::new
- ::pushEpisodeTrace::push
- ::returnsEpisodeTrace::returns
- ::total_rewardEpisodeTrace::total_reward
- ::choose_actionEpsilonGreedyPolicy::choose_action
- ::newEpsilonGreedyPolicy::new
- ::newEpsilonSchedule::new
- ::valueEpsilonSchedule::value
- ::valuesEpsilonSchedule::values
- ::newEvaluationConfig::new
- ::with_windowEvaluationConfig::with_window
T
EvaluationPoint
- ::choose_actionExpectedSARSAAgent::choose_action
- ::epsilonExpectedSARSAAgent::epsilon
- ::learnExpectedSARSAAgent::learn
- ::newExpectedSARSAAgent::new
- ::q_reportExpectedSARSAAgent::q_report
- ::reset_episodeExpectedSARSAAgent::reset_episode
- ::reportExperimentSummary::report
- ::actionsGridWorldEnv::actions
- ::newGridWorldEnv::new
- ::renderGridWorldEnv::render
- ::state_spaceGridWorldEnv::state_space
- ::stepGridWorldEnv::step
T
LcgRng
- ::newLearningRateSchedule::new
- ::valueLearningRateSchedule::value
- ::finished_countMemoryLogger::finished_count
- ::newMemoryLogger::new
- ::started_countMemoryLogger::started_count
- ::transition_countMemoryLogger::transition_count
- ::choose_actionMonteCarloAgent::choose_action
- ::learn_episodeMonteCarloAgent::learn_episode
- ::newMonteCarloAgent::new
- ::q_valueMonteCarloAgent::q_value
- ::visit_countMonteCarloAgent::visit_count
- ::valuePolicyEvaluation::value
- ::choose_actionQLearningAgent::choose_action
- ::epsilonQLearningAgent::epsilon
- ::learnQLearningAgent::learn
- ::newQLearningAgent::new
- ::q_reportQLearningAgent::q_report
- ::q_valueQLearningAgent::q_value
- ::reset_episodeQLearningAgent::reset_episode
- ::set_q_valueQLearningAgent::set_q_value
T
QTable
- ::actionsRandomWalkEnv::actions
- ::newRandomWalkEnv::new
- ::renderRandomWalkEnv::render
- ::resetRandomWalkEnv::reset
- ::state_spaceRandomWalkEnv::state_space
- ::stepRandomWalkEnv::step
- ::atReplayBuffer::at
- ::is_fullReplayBuffer::is_full
- ::lengthReplayBuffer::length
- ::mean_rewardReplayBuffer::mean_reward
- ::newReplayBuffer::new
- ::prioritiesReplayBuffer::priorities
- ::pushReplayBuffer::push
T
ReplayItem
- ::add_rowReportTable::add_row
- ::column_countReportTable::column_count
- ::newReportTable::new
- ::row_countReportTable::row_count
- ::to_csvReportTable::to_csv
- ::to_markdownReportTable::to_markdown
- ::valid_shapeReportTable::valid_shape
- ::averageRunningStats::average
- ::newRunningStats::new
- ::pushRunningStats::push
- ::standard_errorRunningStats::standard_error
- ::summaryRunningStats::summary
- ::varianceRunningStats::variance
- ::choose_actionSARSAAgent::choose_action
- ::epsilonSARSAAgent::epsilon
- ::learnSARSAAgent::learn
- ::newSARSAAgent::new
- ::q_reportSARSAAgent::q_report
- ::reset_episodeSARSAAgent::reset_episode
- ::errorScorecard::error
- ::newScorecard::new
- ::passedScorecard::passed
- ::textScorecard::text
- ::addScorecardSet::add
- ::failed_countScorecardSet::failed_count
- ::newScorecardSet::new
- ::passedScorecardSet::passed
- ::to_textScorecardSet::to_text
- ::atSeedBank::at
- ::csvSeedBank::csv
- ::distinctSeedBank::distinct
- ::lengthSeedBank::length
- ::newSeedBank::new
- ::newTrainer::new
- ::trainTrainer::train
- ::train_q_learningTrainer::train_q_learning
- ::train_sarsaTrainer::train_sarsa
- ::compact_lineTrainingReport::compact_line
- ::episode_countTrainingReport::episode_count
- ::final_epsilon_valueTrainingReport::final_epsilon_value
- ::goal_countTrainingReport::goal_count
- ::reward_atTrainingReport::reward_at
- ::steps_atTrainingReport::steps_at
- ::actionTransition::action
- ::doneTransition::done
- ::newTransition::new
- ::next_stateTransition::next_state
- ::rewardTransition::reward
- ::stateTransition::state
- ::step_indexTransition::step_index
T
ValidationFinding
- ::addValidationReport::add
- ::finding_countValidationReport::finding_count
- ::newValidationReport::new
- ::okValidationReport::ok
- ::summaryValidationReport::summary
- ::to_textValidationReport::to_text
T
ValidationSeverity
- ::actionValueIterationResult::action
- ::greedy_pathValueIterationResult::greedy_path
- ::valueValueIterationResult::value
V
acceptance_evidence
V
action_map_text
V
all_environment_audits
V
audit_score
V
benchmark_catalog
V
benchmark_manifest
V
boundary_probe
V
clipped
V
compact_result_line
V
compact_results
V
compare_results_table
V
compare_training_reports
V
confidence_interval
V
csv_escape
V
discounted_return
V
discounted_returns
V
evaluate_grid_policy
V
full_benchmark_report
V
greedy_action_map
V
gridworld_value_iteration
V
join_lines
V
linear_interpolate
V
markdown_escape
V
merge_reward_series
V
moving_average
V
normalize_returns
V
percentile
V
performance_budget
V
policy_agreement
V
policy_histogram
V
project_name
V
project_self_check
V
q_table_snapshot
V
quality_text
V
regret
V
release_checklist_text
V
report_contract
V
report_footer
V
report_header
V
report_quality
V
report_sections
V
report_sections_text
V
report_table_from_result
V
report_table_from_stats
V
report_version
V
reproducibility_signature
V
result_digest
V
result_episode_ids
V
result_has_consistent_ids
V
result_has_learning_signal
V
result_health
V
result_is_nontrivial
V
result_range
V
reward_ceiling
V
reward_floor
V
risk_flags
V
run_bandit_benchmark
V
run_cliff_benchmark
V
run_demo
V
run_gridworld_benchmark
V
run_random_walk_benchmark
V
run_sarsa_demo
V
run_standard_reports
V
seed_sensitivity
V
solved_prefix
V
source_scale_estimate
V
stable_mean
V
stable_sum
V
standard_benchmarks
V
suite_summary
V
table_is_empty
V
table_last_row
V
table_preview
V
train_cliff_qlearning_generic
V
train_gridworld_expected_sarsa_generic
V
train_gridworld_qlearning_generic
V
train_gridworld_sarsa_generic
V
train_with_memory_logger
V
trend
V
tutorial_blurb
V
validate_cliff
V
validate_config
V
validate_gridworld
V
validate_planner
V
validate_policy
V
validate_replay
V
validate_result
V
validate_schedule
V
value_error