List of all items

Structs

• buffer::ExperienceRecord
• buffer::columnar::ExperienceTable
• buffer::concurrent::ConcurrentReplayBuffer
• buffer::episode::EpisodeMeta
• buffer::episode::EpisodeTracker
• buffer::episode::EpisodeWindow
• buffer::extra_columns::ColumnHandle
• buffer::extra_columns::ExtraColumns
• buffer::her::HERBuffer
• buffer::mmap::MmapReplayBuffer
• buffer::offline::DatasetStats
• buffer::offline::OfflineBatch
• buffer::offline::OfflineDatasetBuffer
• buffer::offline::TrajectoryBatch
• buffer::priority::LAPConfig
• buffer::priority::PrioritizedReplayBuffer
• buffer::priority::PrioritizedSampledBatch
• buffer::priority::SumTree
• buffer::provenance::TransitionMeta
• buffer::ringbuf::ReplayBuffer
• buffer::ringbuf::SampledBatch
• buffer::sequence::SequenceBatch
• buffer::sequence::SequenceReplayBuffer
• buffer::varlen::VarLenStore
• env::Transition
• env::builtins::CartPole
• env::builtins::Pendulum
• env::mujoco::SimplifiedMuJoCoEnv
• env::parallel::BatchTransition
• env::parallel::VecEnv
• llm::ops::DPOPair
• pipeline::channel::Pipeline
• pipeline::channel::RolloutBatch
• pipeline::collector::AsyncCollector
• training::augmentation::RandomShift
• training::gae::GaeResult
• training::kl::KLController
• training::normalization::RunningStats
• training::normalization::RunningStatsVec
• training::packing::PackedBatch
• training::reward_shaping::GoalDistanceTransform
• training::reward_shaping::PBRSTransform
• training::reward_shaping::RewardContext
• training::weight_ops::PolyakUpdate
• training::weight_ops::ReptileUpdate

Enums

• buffer::her::HERStrategy
• env::spaces::Action
• env::spaces::ActionSpace
• env::spaces::ObsSpace
• env::spaces::Observation
• error::RloxError

Traits

• buffer::episode::EpisodeAware
• env::RLEnv
• env::batch::BatchSteppable
• training::augmentation::ImageAugmentation
• training::reward_shaping::RewardTransform
• training::weight_ops::WeightUpdate

Functions

• buffer::her::sparse_goal_reward
• buffer::mixed::sample_mixed
• buffer::priority::compute_lap_priorities
• buffer::priority::compute_td_priorities
• llm::ops::f32_ops::compute_batch_group_advantages
• llm::ops::f32_ops::compute_batch_token_kl
• llm::ops::f32_ops::compute_batch_token_kl_schulman
• llm::ops::f32_ops::compute_group_advantages
• llm::ops::f32_ops::compute_token_kl
• llm::ops::f32_ops::compute_token_kl_schulman
• llm::ops::f64_ops::compute_batch_group_advantages
• llm::ops::f64_ops::compute_batch_token_kl
• llm::ops::f64_ops::compute_batch_token_kl_schulman
• llm::ops::f64_ops::compute_group_advantages
• llm::ops::f64_ops::compute_token_kl
• llm::ops::f64_ops::compute_token_kl_schulman
• seed::derive_seed
• seed::rng_from_seed
• training::augmentation::random_shift_batch
• training::gae::compute_gae
• training::gae::compute_gae_batched
• training::gae::compute_gae_batched_f32
• training::packing::pack_sequences
• training::reward_shaping::compute_goal_distance_potentials
• training::reward_shaping::shape_rewards_pbrs
• training::simd_ops::average_weights_simd
• training::simd_ops::compute_priorities_simd
• training::simd_ops::copy_pixel_row
• training::simd_ops::pbrs_simd
• training::simd_ops::polyak_update_simd
• training::simd_ops::reptile_update_simd
• training::vtrace::compute_vtrace
• training::weight_ops::average_weight_vectors
• training::weight_ops::polyak_update
• training::weight_ops::reptile_update