List of all items
Structs
- Steps
- agents::AgentPair
- agents::BetaThompsonSamplingAgentConfig
- agents::RandomAgent
- agents::RandomAgentConfig
- agents::ResettingMetaAgent
- agents::ResettingMetaAgentConfig
- agents::SerialActorAgent
- agents::TabularQLearningAgentConfig
- agents::UCB1AgentConfig
- agents::buffers::HistoryDataBound
- agents::buffers::NullBuffer
- agents::buffers::ReplayBuffer
- agents::buffers::VecBuffer
- agents::finite::FiniteSpaceActor
- agents::finite::FiniteSpaceAgent
- agents::finite::FiniteSpaceBuffer
- envs::Bandit
- envs::CartPole
- envs::CartPoleConfig
- envs::Chain
- envs::DirichletRandomMdps
- envs::FirstPlayerView
- envs::FruitGame
- envs::LatentStepLimit
- envs::MemoryGame
- envs::OneHotBandits
- envs::PartitionGame
- envs::SecondPlayerView
- envs::StoredEnvStructure
- envs::UniformBernoulliBandits
- envs::VisibleStepLimit
- envs::Wrapped
- envs::fruit::AssistantObs
- envs::fruit::AssistantObsSpace
- envs::fruit::FruitGame
- envs::fruit::FruitGameState
- envs::fruit::PrincipalObs
- envs::fruit::PrincipalObsSpace
- envs::meta::InnerEnvStructure
- envs::meta::InnerStepObs
- envs::meta::InnerStepObsSpace
- envs::meta::MetaEnv
- envs::meta::MetaObservation
- envs::meta::MetaObservationSpace
- envs::meta::MetaState
- envs::meta::TrialEpisodeLimit
- feedback::Reward
- logging::ByCounter
- logging::ByTime
- logging::ChunkLogger
- logging::DisplayBackend
- logging::DisplayLogger
- logging::Id
- logging::LogGroup
- logging::ScopedLogger
- logging::TensorBoardBackend
- logging::TensorBoardLogger
- simulation::LogSteps
- simulation::MapTransient
- simulation::OnlineStepsSummary
- simulation::Step
- simulation::Steps
- simulation::StepsSummary
- simulation::TakeAlignedSteps
- simulation::TakeEpisodes
- simulation::TrainParallelConfig
- spaces::ArraySpace
- spaces::BooleanSpace
- spaces::IndexSpace
- spaces::IndexedTypeSpace
- spaces::IntervalSpace
- spaces::NdArraySpace
- spaces::NonEmptyFeatures
- spaces::OptionSpace
- spaces::PowerSpace
- spaces::SingletonSpace
- spaces::TupleSpace2
- spaces::TupleSpace3
- spaces::TupleSpace4
- spaces::TupleSpace5
- torch::ExclusiveTensor
- torch::agents::ActorCriticAgent
- torch::agents::ActorCriticConfig
- torch::agents::DqnActor
- torch::agents::DqnAgent
- torch::agents::DqnConfig
- torch::agents::WithCpuCopy
- torch::agents::critics::RewardToGo
- torch::agents::critics::RewardToGoConfig
- torch::agents::critics::ValuesOpt
- torch::agents::critics::ValuesOptConfig
- torch::agents::features::LazyHistoryFeatures
- torch::agents::policies::PolicyActor
- torch::agents::policies::Ppo
- torch::agents::policies::PpoConfig
- torch::agents::policies::Reinforce
- torch::agents::policies::ReinforceConfig
- torch::agents::policies::Trpo
- torch::agents::policies::TrpoConfig
- torch::backends::WithCudnnEnabled
- torch::distributions::Bernoulli
- torch::distributions::Categorical
- torch::distributions::DeterministicEmptyVec
- torch::initializers::TensorBuilder
- torch::modules::BatchMap
- torch::modules::Chain
- torch::modules::ChainConfig
- torch::modules::Linear
- torch::modules::LinearConfig
- torch::modules::Mlp
- torch::modules::MlpConfig
- torch::modules::SeqIterator
- torch::optimizers::AdamConfig
- torch::optimizers::AdamWConfig
- torch::optimizers::ConjugateGradientOptimizer
- torch::optimizers::ConjugateGradientOptimizerConfig
- torch::optimizers::RmsPropConfig
- torch::optimizers::SgdConfig
- torch::packed::BatchSizes
- torch::packed::PackedSeqIter
- torch::packed::PackedTensor
- torch::packed::SharedBatchSizes
- torch::serialize::TensorDef
- utils::coord_vector::CoordVector
- utils::distributions::Bernoulli
- utils::distributions::Deterministic
- utils::fmt::DisplayFn
- utils::fmt::Frequency
- utils::fmt::PrettyPrint
- utils::iter::Differences
- utils::iter::RandSubsample
- utils::iter::SizedChain
- utils::iter::SplitChunksByLength
- utils::order::ExpectOrd
- utils::slice::SplitSlice
- utils::stats::OnlineMeanVariance
Enums
- agents::ActorMode
- agents::BuildAgentError
- agents::buffers::WriteExperienceError
- envs::BuildEnvError
- envs::Successor
- envs::fruit::CellView
- envs::fruit::Fruit
- envs::fruit::Move
- logging::LogError
- logging::LogValue
- simulation::SimSeed
- torch::agents::critics::AdvantageFn
- torch::agents::critics::StepValueTarget
- torch::agents::schedules::DataCollectionSchedule
- torch::agents::schedules::ExplorationRateSchedule
- torch::initializers::InitializeTensorError
- torch::initializers::Initializer
- torch::initializers::VarianceScale
- torch::modules::Activation
- torch::optimizers::OptimizerStepError
- torch::packed::PackedStructure
- torch::packed::PackingError
- torch::serialize::ByteOrder
- torch::serialize::DeviceDef
- torch::serialize::KindDef
- utils::borrow::ReadOnly
- utils::iter::PartialMaxError
Traits
- BuildEnv
- agents::Actor
- agents::Agent
- agents::BatchUpdate
- agents::BuildAgent
- agents::buffers::WriteExperience
- agents::buffers::WriteExperienceIncremental
- envs::BuildEnv
- envs::BuildEnvDist
- envs::CloneBuild
- envs::EnvDistribution
- envs::EnvStructure
- envs::Environment
- envs::Pomdp
- envs::PomdpStructure
- envs::StructurePreservingWrapper
- envs::StructuredEnvDist
- envs::StructuredEnvironment
- envs::Wrap
- envs::meta::InnerEpisodeDone
- envs::meta::MetaFeedback
- envs::meta::MetaFeedbackSpace
- feedback::Feedback
- feedback::Summary
- logging::Loggable
- logging::StatsLogger
- simulation::Simulation
- simulation::StepsIter
- spaces::FeatureSpace
- spaces::FiniteSpace
- spaces::Indexed
- spaces::LogElementSpace
- spaces::NonEmptySpace
- spaces::ParameterizedDistributionSpace
- spaces::ReprSpace
- spaces::SampleSpace
- spaces::Space
- spaces::SubsetOrd
- torch::agents::critics::BuildCritic
- torch::agents::critics::Critic
- torch::agents::features::HistoryFeatures
- torch::agents::policies::BuildPolicy
- torch::agents::policies::Policy
- torch::modules::AsModule
- torch::modules::BuildModule
- torch::modules::Forward
- torch::modules::Module
- torch::modules::ModuleExtras
- torch::modules::SeqIterative
- torch::modules::SeqPacked
- torch::modules::SeqSerial
- torch::optimizers::BaseOptimizer
- torch::optimizers::BuildOptimizer
- torch::optimizers::Optimizer
- torch::optimizers::TrustRegionOptimizer
- utils::any::AsAny
- utils::distributions::ArrayDistribution
- utils::distributions::Bounded
- utils::distributions::FromMean
- utils::iter::ArgMaxBy
- utils::iter::PartialMax
- utils::num_array::BuildFromArray1D
- utils::num_array::BuildFromArray2D
- utils::num_array::NumArray1D
- utils::num_array::NumArray2D
- utils::sequence::Sequence
- utils::sequence::TakePrefx
Derive Macros
- spaces::FiniteSpace
- spaces::Indexed
- spaces::LogElementSpace
- spaces::ProductSpace
- spaces::SampleSpace
- spaces::Space
- spaces::SubsetOrd
Functions
- simulation::train_parallel
- simulation::train_serial
- spaces::iter_product_subset_ord
- spaces::product_subset_ord
- torch::agents::critics::eval_extended_state_values
- torch::agents::critics::gae
- torch::agents::critics::one_step_values
- torch::agents::critics::reward_to_go
- torch::agents::critics::temporal_differences
- torch::optimizers::opt_expect_ok_log
- torch::utils::f_flat_dot
- torch::utils::f_flatten_tensors
- torch::utils::f_unflatten_tensors
- torch::utils::flat_dot
- torch::utils::flatten_tensors
- torch::utils::unflatten_tensors
- train_parallel
- train_serial
Typedefs
- Prng
- agents::BetaThompsonSamplingAgent
- agents::TabularQLearningAgent
- agents::UCB1Agent
- envs::BernoulliBandit
- envs::DeterministicBandit
- envs::PartialSuccessor
- envs::RefSuccessor
- envs::WithLatentStepLimit
- envs::WithVisibleStepLimit
- envs::fruit::Cell
- envs::fruit::GridVec
- envs::fruit::JointObsSpace
- envs::fruit::VisibleGridSpace
- simulation::PartialStep
- simulation::TransientStep
- spaces::Array1Space
- spaces::Array2Space
- spaces::Array3Space
- spaces::BoxSpace
- torch::modules::Gru
- torch::modules::GruConfig
- torch::modules::GruMlpConfig
- torch::modules::Lstm
- torch::modules::LstmConfig
- torch::modules::LstmMlpConfig
- utils::slice::SplitSliceIter