hmyhmyhmyss/moontrajectory/cmd/main

README
- ::batch_countBatchCursor::batch_count
- ::batch_sizeBatchCursor::batch_size
- ::has_nextBatchCursor::has_next
- ::newBatchCursor::new
- ::next_indicesBatchCursor::next_indices
- ::positionBatchCursor::position
- ::remainingBatchCursor::remaining
- ::resetBatchCursor::reset
- ::totalBatchCursor::total
- ::episodesBenchmarkCase::episodes
- ::nameBenchmarkCase::name
- ::newBenchmarkCase::new
- ::reward_scaleBenchmarkCase::reward_scale
- ::steps_per_episodeBenchmarkCase::steps_per_episode
- ::total_stepsBenchmarkCase::total_steps
- ::actionsEpisode::actions
- ::count_terminalsEpisode::count_terminals
- ::discounted_returnsEpisode::discounted_returns
- ::discounted_returns_with_bootstrapEpisode::discounted_returns_with_bootstrap
- ::first_transitionEpisode::first_transition
- ::from_transitionsEpisode::from_transitions
- ::is_emptyEpisode::is_empty
- ::is_terminatedEpisode::is_terminated
- ::is_truncatedEpisode::is_truncated
- ::last_transitionEpisode::last_transition
- ::lenEpisode::len
- ::mark_terminatedEpisode::mark_terminated
- ::mark_truncatedEpisode::mark_truncated
- ::n_step_transitionsEpisode::n_step_transitions
- ::newEpisode::new
- ::pushEpisode::push
- ::reward_statsEpisode::reward_stats
- ::rewardsEpisode::rewards
- ::statesEpisode::states
- ::terminal_indexEpisode::terminal_index
- ::total_rewardEpisode::total_reward
- ::transitionsEpisode::transitions
- ::validateEpisode::validate
- ::windowEpisode::window
- ::windowsEpisode::windows
- ::all_non_terminalEpisodeWindow::all_non_terminal
- ::contains_terminalEpisodeWindow::contains_terminal
- ::discounted_rewardEpisodeWindow::discounted_reward
- ::firstEpisodeWindow::first
- ::is_emptyEpisodeWindow::is_empty
- ::is_terminalEpisodeWindow::is_terminal
- ::itemsEpisodeWindow::items
- ::lastEpisodeWindow::last
- ::lengthEpisodeWindow::length
- ::offsetEpisodeWindow::offset
- ::rewardsEpisodeWindow::rewards
- ::state_countEpisodeWindow::state_count
- ::terminal_indexEpisodeWindow::terminal_index
- ::total_rewardEpisodeWindow::total_reward
- ::best_rewardEvaluationReport::best_reward
- ::episodesEvaluationReport::episodes
- ::mean_rewardEvaluationReport::mean_reward
- ::terminatedEvaluationReport::terminated
- ::total_rewardEvaluationReport::total_reward
- ::total_stepsEvaluationReport::total_steps
- ::truncatedEvaluationReport::truncated
- ::worst_rewardEvaluationReport::worst_reward
- ::decay_stepsExponentialSchedule::decay_steps
- ::final_valueExponentialSchedule::final_value
- ::initialExponentialSchedule::initial
- ::newExponentialSchedule::new
- ::valueExponentialSchedule::value
- ::durationLinearSchedule::duration
- ::endLinearSchedule::end
- ::newLinearSchedule::new
- ::startLinearSchedule::start
- ::valueLinearSchedule::value
- ::capacityPrioritizedReplayBuffer::capacity
- ::clearPrioritizedReplayBuffer::clear
- ::count_priority_at_leastPrioritizedReplayBuffer::count_priority_at_least
- ::effective_priority_sumPrioritizedReplayBuffer::effective_priority_sum
- ::extend_episodePrioritizedReplayBuffer::extend_episode
- ::getPrioritizedReplayBuffer::get
- ::is_emptyPrioritizedReplayBuffer::is_empty
- ::lenPrioritizedReplayBuffer::len
- ::newPrioritizedReplayBuffer::new
- ::priority_atPrioritizedReplayBuffer::priority_at
- ::priority_distributionPrioritizedReplayBuffer::priority_distribution
- ::priority_maxPrioritizedReplayBuffer::priority_max
- ::priority_sumPrioritizedReplayBuffer::priority_sum
- ::pushPrioritizedReplayBuffer::push
- ::sample_batchPrioritizedReplayBuffer::sample_batch
- ::to_arrayPrioritizedReplayBuffer::to_array
- ::update_priorityPrioritizedReplayBuffer::update_priority
- ::with_paramsPrioritizedReplayBuffer::with_params
T
PrioritizedSample
- ::all_sequencesReplayBuffer::all_sequences
- ::capacityReplayBuffer::capacity
- ::clearReplayBuffer::clear
- ::count_reward_at_leastReplayBuffer::count_reward_at_least
- ::count_reward_belowReplayBuffer::count_reward_below
- ::extend_episodeReplayBuffer::extend_episode
- ::getReplayBuffer::get
- ::is_emptyReplayBuffer::is_empty
- ::is_fullReplayBuffer::is_full
- ::lenReplayBuffer::len
- ::newReplayBuffer::new
- ::newestReplayBuffer::newest
- ::oldestReplayBuffer::oldest
- ::pushReplayBuffer::push
- ::reportReplayBuffer::report
- ::reward_histogramReplayBuffer::reward_histogram
- ::sample_allReplayBuffer::sample_all
- ::sample_batchReplayBuffer::sample_batch
- ::sample_sequencesReplayBuffer::sample_sequences
- ::sequenceReplayBuffer::sequence
- ::terminal_indicesReplayBuffer::terminal_indices
- ::to_arrayReplayBuffer::to_array
- ::valid_sequence_startsReplayBuffer::valid_sequence_starts
- ::capacityReplayReport::capacity
- ::maximum_rewardReplayReport::maximum_reward
- ::mean_rewardReplayReport::mean_reward
- ::minimum_rewardReplayReport::minimum_reward
- ::occupancyReplayReport::occupancy
- ::sizeReplayReport::size
- ::terminal_countReplayReport::terminal_count
- ::total_rewardReplayReport::total_reward
- ::newReplayRng::new
- ::next_indexReplayRng::next_index
- ::next_stateReplayRng::next_state
- ::next_unitReplayRng::next_unit
T
ReplaySample
- ::countRewardStats::count
- ::emptyRewardStats::empty
- ::maximumRewardStats::maximum
- ::meanRewardStats::mean
- ::minimumRewardStats::minimum
- ::negative_countRewardStats::negative_count
- ::positive_countRewardStats::positive_count
- ::sumRewardStats::sum
- ::zero_countRewardStats::zero_count
- ::is_paddedSequenceSample::is_padded
- ::lengthSequenceSample::length
- ::maskSequenceSample::mask
- ::rewardsSequenceSample::rewards
- ::startSequenceSample::start
- ::terminalsSequenceSample::terminals
- ::transitionsSequenceSample::transitions
- ::valid_lengthSequenceSample::valid_length
- ::lengthTargetBatch::length
- ::maskTargetBatch::mask
- ::valuesTargetBatch::values
- ::addTrajectoryDataset::add
- ::add_uncheckedTrajectoryDataset::add_unchecked
- ::appendTrajectoryDataset::append
- ::count_with_reward_at_leastTrajectoryDataset::count_with_reward_at_least
- ::count_with_terminalTrajectoryDataset::count_with_terminal
- ::discounted_returnsTrajectoryDataset::discounted_returns
- ::drop_episodesTrajectoryDataset::drop_episodes
- ::episode_countTrajectoryDataset::episode_count
- ::episode_lengthsTrajectoryDataset::episode_lengths
- ::episode_reward_rangeTrajectoryDataset::episode_reward_range
- ::episodesTrajectoryDataset::episodes
- ::filter_by_lengthTrajectoryDataset::filter_by_length
- ::filter_by_rewardTrajectoryDataset::filter_by_reward
- ::flattenTrajectoryDataset::flatten
- ::from_episodesTrajectoryDataset::from_episodes
- ::getTrajectoryDataset::get
- ::is_emptyTrajectoryDataset::is_empty
- ::longest_episodeTrajectoryDataset::longest_episode
- ::mean_episode_lengthTrajectoryDataset::mean_episode_length
- ::newTrajectoryDataset::new
- ::reward_per_stepTrajectoryDataset::reward_per_step
- ::reward_statsTrajectoryDataset::reward_stats
- ::sample_episodesTrajectoryDataset::sample_episodes
- ::shortest_episodeTrajectoryDataset::shortest_episode
- ::split_atTrajectoryDataset::split_at
- ::take_episodesTrajectoryDataset::take_episodes
- ::terminal_episode_countTrajectoryDataset::terminal_episode_count
- ::terminal_rateTrajectoryDataset::terminal_rate
- ::transition_countTrajectoryDataset::transition_count
- ::truncated_episode_countTrajectoryDataset::truncated_episode_count
- ::truncation_rateTrajectoryDataset::truncation_rate
- ::newTransition::new
- ::non_terminalTransition::non_terminal
- ::terminalTransition::terminal
- ::maximumWarmupCosineSchedule::maximum
- ::minimumWarmupCosineSchedule::minimum
- ::newWarmupCosineSchedule::new
- ::total_stepsWarmupCosineSchedule::total_steps
- ::valueWarmupCosineSchedule::value
- ::warmup_stepsWarmupCosineSchedule::warmup_steps
V
array_cumulative
V
array_difference
V
array_drop
V
array_l1_distance
V
array_l2_squared_distance
V
array_mask
V
array_max
V
array_mean
V
array_min
V
array_pad
V
array_scale_add
V
array_sum
V
array_take
V
array_weighted_average
V
benchmark_case_by_name
V
benchmark_cases
V
benchmark_reward_scales
V
benchmark_summary
V
benchmark_workload_size
V
clip_values
V
discounted_prefixes
V
discounted_sum
V
episode_lengths_histogram
V
episode_reward_histogram
V
evaluate_episodes
V
generalized_advantages
V
generate_benchmark_dataset
V
normalize_values
V
scale_rewards
V
schedule_delta
V
schedule_is_finished
V
schedule_progress
V
schedule_values
V
success_rate
V
target_batches
V
td_targets