Index _ | A | B | C | D | E | F | G | H | I | L | M | N | O | P | R | S | T | U | V | W | X | Z _ __getattr__() (duo_ai.algorithms.ppo.TrainBuffer method) __getitem__() (duo_ai.algorithms.ppo.TensorDict method) __post_init__() (duo_ai.core.config.MasterConfig method) (duo_ai.MasterConfig method) (duo_ai.policies.ppo.PPOPolicyConfig method) __setitem__() (duo_ai.algorithms.ppo.TensorDict method) (duo_ai.algorithms.ppo.TrainBuffer method) (duo_ai.utils.wandb.WandbLogger method) __version__ (in module duo_ai) _compute_advantages_and_returns() (duo_ai.algorithms.ppo.PPOAlgorithm method) (duo_ai.algorithms.PPOAlgorithm method) _compute_agents_action() (duo_ai.core.environment.GeneralCoordEnv method) (duo_ai.GeneralCoordEnv method) _compute_base_action() (duo_ai.CoordEnv method) (duo_ai.core.CoordEnv method) (duo_ai.core.environment.CoordEnv method) (duo_ai.core.environment.GeneralCoordEnv method) (duo_ai.GeneralCoordEnv method) _eval_one_iteration() (duo_ai.core.Evaluator method) (duo_ai.core.evaluator.Evaluator method) (duo_ai.Evaluator method) _generate_data() (duo_ai.algorithms.pyod.PyODAlgorithm method) (duo_ai.algorithms.PyODAlgorithm method) _generate_scores() (duo_ai.algorithms.logit.LogitAlgorithm method) (duo_ai.algorithms.LogitAlgorithm method) _get_fc_input_size() (duo_ai.models.impala.Impala method) _get_obs() (duo_ai.CoordEnv method) (duo_ai.core.CoordEnv method) (duo_ai.core.environment.CoordEnv method) (duo_ai.core.environment.GeneralCoordEnv method) (duo_ai.GeneralCoordEnv method) _get_pyod_class() (duo_ai.policies.pyod.PyODPolicy method) (duo_ai.policies.PyODPolicy method) _get_reward() (duo_ai.CoordEnv method) (duo_ai.core.CoordEnv method) (duo_ai.core.environment.CoordEnv method) _initialize() (duo_ai.algorithms.ppo.PPOAlgorithm method) (duo_ai.algorithms.PPOAlgorithm method) _make_input() (duo_ai.policies.pyod.PyODPolicy method) (duo_ai.policies.PyODPolicy method) _reset_agents() (duo_ai.CoordEnv method) (duo_ai.core.CoordEnv method) (duo_ai.core.environment.CoordEnv method) _train_once() (duo_ai.algorithms.ppo.PPOAlgorithm method) (duo_ai.algorithms.PPOAlgorithm method) _update_learning_rate() (duo_ai.algorithms.ppo.PPOAlgorithm method) (duo_ai.algorithms.PPOAlgorithm method) A accept_rate (duo_ai.algorithms.pyod.PyODAlgorithmConfig attribute) act() (duo_ai.core.Policy method) (duo_ai.core.policy.Policy method) (duo_ai.policies.always.AlwaysPolicy method) (duo_ai.policies.AlwaysPolicy method) (duo_ai.policies.logit.LogitPolicy method) (duo_ai.policies.LogitPolicy method) (duo_ai.policies.ppo.PPOPolicy method) (duo_ai.policies.PPOPolicy method) (duo_ai.policies.pyod.PyODPolicy method) (duo_ai.policies.PyODPolicy method) (duo_ai.policies.random.RandomPolicy method) (duo_ai.policies.RandomPolicy method) action_space (duo_ai.CoordEnv attribute) (duo_ai.core.CoordEnv attribute) (duo_ai.core.environment.CoordEnv attribute) actions (duo_ai.algorithms.ppo.PPOBatch attribute) add() (duo_ai.algorithms.ppo.TrainBuffer method) (duo_ai.utils.wandb.WandbLogger method) add_episode_step() (duo_ai.algorithms.ppo.PPOTrainSummarizer method) (duo_ai.core.evaluator.EvaluationSummarizer method) add_training_iteration() (duo_ai.algorithms.ppo.PPOTrainSummarizer method) advantages (duo_ai.algorithms.ppo.PPOBatch attribute) agent (duo_ai.policies.always.AlwaysPolicyConfig attribute) Algorithm (class in duo_ai.core) (class in duo_ai.core.algorithm) algorithm (duo_ai.core.config.MasterConfig attribute) (duo_ai.MasterConfig attribute) AlwaysAlgorithm (class in duo_ai.algorithms) (class in duo_ai.algorithms.always) AlwaysAlgorithmConfig (class in duo_ai.algorithms.always) AlwaysPolicy (class in duo_ai.policies) (class in duo_ai.policies.always) AlwaysPolicyConfig (class in duo_ai.policies.always) anneal_lr (duo_ai.algorithms.ppo.PPOAlgorithmConfig attribute) B base_env (duo_ai.CoordEnv attribute) (duo_ai.core.CoordEnv attribute) (duo_ai.core.environment.CoordEnv attribute) block1 (duo_ai.models.impala.Impala attribute) block2 (duo_ai.models.impala.Impala attribute) block3 (duo_ai.models.impala.Impala attribute) C choice (duo_ai.policies.always.AlwaysPolicy attribute) (duo_ai.policies.AlwaysPolicy attribute) clear() (duo_ai.algorithms.ppo.PPOTrainSummarizer method) (duo_ai.core.evaluator.EvaluationSummarizer method) (duo_ai.utils.wandb.WandbLogger method) clf (duo_ai.policies.pyod.PyODPolicy attribute) (duo_ai.policies.PyODPolicy attribute) clip_coef (duo_ai.algorithms.ppo.PPOAlgorithmConfig attribute) clip_vloss (duo_ai.algorithms.ppo.PPOAlgorithmConfig attribute) close() (duo_ai.CoordEnv method) (duo_ai.core.CoordEnv method) (duo_ai.core.environment.CoordEnv method) cls (duo_ai.policies.random.RandomPolicyConfig attribute) compute_confidence() (duo_ai.policies.logit.LogitPolicy method) (duo_ai.policies.LogitPolicy method) config (duo_ai.algorithms.logit.LogitAlgorithm attribute) (duo_ai.algorithms.LogitAlgorithm attribute) (duo_ai.algorithms.ppo.PPOAlgorithm attribute) (duo_ai.algorithms.PPOAlgorithm attribute) (duo_ai.algorithms.pyod.PyODAlgorithm attribute) (duo_ai.algorithms.PyODAlgorithm attribute) (duo_ai.algorithms.random.RandomAlgorithm attribute) (duo_ai.algorithms.RandomAlgorithm attribute) (duo_ai.CoordEnv attribute) (duo_ai.core.CoordEnv attribute) (duo_ai.core.environment.CoordEnv attribute) (duo_ai.core.Evaluator attribute) (duo_ai.core.evaluator.Evaluator attribute) (duo_ai.Evaluator attribute) (duo_ai.policies.always.AlwaysPolicy attribute) (duo_ai.policies.AlwaysPolicy attribute) (duo_ai.policies.logit.LogitPolicy attribute) (duo_ai.policies.LogitPolicy attribute) (duo_ai.policies.ppo.PPOPolicy attribute) (duo_ai.policies.PPOPolicy attribute) (duo_ai.policies.pyod.PyODPolicy attribute) (duo_ai.policies.PyODPolicy attribute) (duo_ai.policies.random.RandomPolicy attribute) (duo_ai.policies.RandomPolicy attribute) config_cls (duo_ai.algorithms.always.AlwaysAlgorithm attribute) (duo_ai.algorithms.AlwaysAlgorithm attribute) (duo_ai.algorithms.logit.LogitAlgorithm attribute) (duo_ai.algorithms.LogitAlgorithm attribute) (duo_ai.algorithms.ppo.PPOAlgorithm attribute) (duo_ai.algorithms.PPOAlgorithm attribute) (duo_ai.algorithms.pyod.PyODAlgorithm attribute) (duo_ai.algorithms.PyODAlgorithm attribute) (duo_ai.algorithms.random.RandomAlgorithm attribute) (duo_ai.algorithms.RandomAlgorithm attribute) (duo_ai.CoordEnv attribute) (duo_ai.core.CoordEnv attribute) (duo_ai.core.environment.CoordEnv attribute) (duo_ai.core.Evaluator attribute) (duo_ai.core.evaluator.Evaluator attribute) (duo_ai.Evaluator attribute) (duo_ai.models.ImpalaCoordPPOModel attribute) (duo_ai.models.ImpalaPPOModel attribute) (duo_ai.models.ppo.ImpalaCoordPPOModel attribute) (duo_ai.models.ppo.ImpalaPPOModel attribute) (duo_ai.policies.always.AlwaysPolicy attribute) (duo_ai.policies.AlwaysPolicy attribute) (duo_ai.policies.logit.LogitPolicy attribute) (duo_ai.policies.LogitPolicy attribute) (duo_ai.policies.ppo.PPOPolicy attribute) (duo_ai.policies.PPOPolicy attribute) (duo_ai.policies.pyod.PyODPolicy attribute) (duo_ai.policies.PyODPolicy attribute) (duo_ai.policies.random.RandomPolicy attribute) (duo_ai.policies.RandomPolicy attribute) configure() (in module duo_ai) (in module duo_ai.core.config) configure_logging() (in module duo_ai.utils.logging) conv (duo_ai.models.impala.ImpalaBlock attribute) conv1 (duo_ai.models.impala.ResidualBlock attribute) conv2 (duo_ai.models.impala.ResidualBlock attribute) CoordEnv (class in duo_ai) (class in duo_ai.core) (class in duo_ai.core.environment) coordination (duo_ai.core.config.MasterConfig attribute) (duo_ai.MasterConfig attribute) CoordinationConfig (class in duo_ai.core.environment) critic_pretrain_steps (duo_ai.algorithms.ppo.PPOAlgorithmConfig attribute) D data (duo_ai.algorithms.ppo.TensorDict attribute) (duo_ai.algorithms.ppo.TrainBuffer attribute) device (duo_ai.core.config.MasterConfig attribute) (duo_ai.MasterConfig attribute) (duo_ai.models.ImpalaCoordPPOModel attribute) (duo_ai.models.ImpalaPPOModel attribute) (duo_ai.models.ppo.ImpalaCoordPPOModel attribute) (duo_ai.models.ppo.ImpalaPPOModel attribute) (duo_ai.policies.always.AlwaysPolicy attribute) (duo_ai.policies.AlwaysPolicy attribute) (duo_ai.policies.logit.LogitPolicy attribute) (duo_ai.policies.LogitPolicy attribute) (duo_ai.policies.pyod.PyODPolicy attribute) (duo_ai.policies.PyODPolicy attribute) (duo_ai.policies.random.RandomPolicy attribute) (duo_ai.policies.RandomPolicy attribute) duo_ai module duo_ai.algorithms module duo_ai.algorithms.always module duo_ai.algorithms.logit module duo_ai.algorithms.ppo module duo_ai.algorithms.pyod module duo_ai.algorithms.random module duo_ai.core module duo_ai.core.algorithm module duo_ai.core.config module duo_ai.core.environment module duo_ai.core.evaluator module duo_ai.core.policy module duo_ai.environments module duo_ai.models module duo_ai.models.impala module duo_ai.models.ppo module duo_ai.policies module duo_ai.policies.always module duo_ai.policies.logit module duo_ai.policies.ppo module duo_ai.policies.pyod module duo_ai.policies.random module duo_ai.utils module duo_ai.utils.evaluation module duo_ai.utils.global_variables module duo_ai.utils.logging module duo_ai.utils.model module duo_ai.utils.wandb module E ElapsedFormatter (class in duo_ai.utils.logging) embedder (duo_ai.models.ImpalaCoordPPOModel attribute) (duo_ai.models.ImpalaPPOModel attribute) (duo_ai.models.ppo.ImpalaCoordPPOModel attribute) (duo_ai.models.ppo.ImpalaPPOModel attribute) ent_coef (duo_ai.algorithms.ppo.PPOAlgorithmConfig attribute) env (duo_ai.core.config.MasterConfig attribute) (duo_ai.core.Evaluator attribute) (duo_ai.core.evaluator.Evaluator attribute) (duo_ai.Evaluator attribute) (duo_ai.MasterConfig attribute) eval() (duo_ai.core.Policy method) (duo_ai.core.policy.Policy method) (duo_ai.policies.always.AlwaysPolicy method) (duo_ai.policies.AlwaysPolicy method) (duo_ai.policies.logit.LogitPolicy method) (duo_ai.policies.LogitPolicy method) (duo_ai.policies.ppo.PPOPolicy method) (duo_ai.policies.PPOPolicy method) (duo_ai.policies.pyod.PyODPolicy method) (duo_ai.policies.PyODPolicy method) (duo_ai.policies.random.RandomPolicy method) (duo_ai.policies.RandomPolicy method) eval_mode (duo_ai.core.config.MasterConfig attribute) (duo_ai.MasterConfig attribute) eval_name (duo_ai.core.config.MasterConfig attribute) (duo_ai.MasterConfig attribute) evaluate() (duo_ai.core.Evaluator method) (duo_ai.core.evaluator.Evaluator method) (duo_ai.Evaluator method) evaluation (duo_ai.core.config.MasterConfig attribute) (duo_ai.MasterConfig attribute) EvaluationSummarizer (class in duo_ai.core.evaluator) Evaluator (class in duo_ai) (class in duo_ai.core) (class in duo_ai.core.evaluator) EvaluatorConfig (class in duo_ai.core.evaluator) experiment_dir (duo_ai.core.config.MasterConfig attribute) (duo_ai.MasterConfig attribute) EXPERT (duo_ai.CoordEnv attribute) expert (duo_ai.CoordEnv attribute) EXPERT (duo_ai.core.CoordEnv attribute) expert (duo_ai.core.CoordEnv attribute) EXPERT (duo_ai.core.environment.CoordEnv attribute) expert (duo_ai.core.environment.CoordEnv attribute) EXPERT (duo_ai.policies.logit.LogitPolicy attribute) (duo_ai.policies.LogitPolicy attribute) (duo_ai.policies.pyod.PyODPolicy attribute) (duo_ai.policies.PyODPolicy attribute) (duo_ai.policies.random.RandomPolicy attribute) (duo_ai.policies.RandomPolicy attribute) expert_query_cost_per_action (duo_ai.CoordEnv attribute) (duo_ai.core.CoordEnv attribute) (duo_ai.core.environment.CoordEnv attribute) expert_query_cost_weight (duo_ai.core.environment.CoordinationConfig attribute) explore_temps (duo_ai.algorithms.logit.LogitAlgorithmConfig attribute) (duo_ai.algorithms.pyod.PyODAlgorithmConfig attribute) F fc (duo_ai.models.impala.Impala attribute) fc_policy (duo_ai.models.ImpalaCoordPPOModel attribute) (duo_ai.models.ImpalaPPOModel attribute) (duo_ai.models.ppo.ImpalaCoordPPOModel attribute) (duo_ai.models.ppo.ImpalaPPOModel attribute) fc_value (duo_ai.models.ImpalaCoordPPOModel attribute) (duo_ai.models.ImpalaPPOModel attribute) (duo_ai.models.ppo.ImpalaCoordPPOModel attribute) (duo_ai.models.ppo.ImpalaPPOModel attribute) feature_type (duo_ai.models.ImpalaCoordPPOModel attribute) (duo_ai.models.ppo.ImpalaCoordPPOModel attribute) (duo_ai.models.ppo.ImpalaCoordPPOModelConfig attribute) (duo_ai.policies.pyod.PyODPolicy attribute) (duo_ai.policies.pyod.PyODPolicyConfig attribute) (duo_ai.policies.PyODPolicy attribute) finalize_episode() (duo_ai.core.evaluator.EvaluationSummarizer method) finalize_iteration() (duo_ai.algorithms.ppo.PPOTrainSummarizer method) fit() (duo_ai.policies.pyod.PyODPolicy method) (duo_ai.policies.PyODPolicy method) Flatten (class in duo_ai.models.impala) flatten() (duo_ai.algorithms.ppo.TensorDict method) (duo_ai.algorithms.ppo.TrainBuffer method) format() (duo_ai.utils.logging.ElapsedFormatter method) format_time() (duo_ai.utils.logging.ElapsedFormatter method) forward() (duo_ai.models.impala.Flatten method) (duo_ai.models.impala.Impala method) (duo_ai.models.impala.ImpalaBlock method) (duo_ai.models.impala.ResidualBlock method) (duo_ai.models.ImpalaCoordPPOModel method) (duo_ai.models.ImpalaPPOModel method) (duo_ai.models.ppo.ImpalaCoordPPOModel method) (duo_ai.models.ppo.ImpalaPPOModel method) from_numpy() (duo_ai.algorithms.ppo.TensorDict class method) G gae_lambda (duo_ai.algorithms.ppo.PPOAlgorithmConfig attribute) gamma (duo_ai.algorithms.ppo.PPOAlgorithmConfig attribute) GeneralCoordEnv (class in duo_ai) (class in duo_ai.core.environment) generate_minibatches() (duo_ai.algorithms.ppo.TrainBuffer method) get() (duo_ai.utils.wandb.WandbLogger method) get_all_global_variables() (in module duo_ai.utils.global_variables) get_global_variable() (in module duo_ai) (in module duo_ai.utils.global_variables) get_params() (duo_ai.core.Policy method) (duo_ai.core.policy.Policy method) (duo_ai.policies.always.AlwaysPolicy method) (duo_ai.policies.AlwaysPolicy method) (duo_ai.policies.logit.LogitPolicy method) (duo_ai.policies.LogitPolicy method) (duo_ai.policies.ppo.PPOPolicy method) (duo_ai.policies.PPOPolicy method) (duo_ai.policies.pyod.PyODPolicy method) (duo_ai.policies.PyODPolicy method) (duo_ai.policies.random.RandomPolicy method) (duo_ai.policies.RandomPolicy method) get_test_eval_info() (in module duo_ai.utils.evaluation) get_train_scores() (duo_ai.policies.pyod.PyODPolicy method) (duo_ai.policies.PyODPolicy method) GLOBAL_VARIABLES (in module duo_ai.utils.global_variables) H hidden (duo_ai.models.ppo.PPOModelOutput attribute) hidden_dim (duo_ai.models.ImpalaPPOModel attribute) (duo_ai.models.ppo.ImpalaPPOModel attribute) I Impala (class in duo_ai.models.impala) ImpalaBlock (class in duo_ai.models.impala) ImpalaCoordPPOModel (class in duo_ai.models) (class in duo_ai.models.ppo) ImpalaCoordPPOModelConfig (class in duo_ai.models.ppo) ImpalaPPOModel (class in duo_ai.models) (class in duo_ai.models.ppo) ImpalaPPOModelConfig (class in duo_ai.models.ppo) initialize_episode() (duo_ai.core.evaluator.EvaluationSummarizer method) initialize_iteration() (duo_ai.algorithms.ppo.PPOTrainSummarizer method) L learning_rate (duo_ai.algorithms.ppo.PPOAlgorithmConfig attribute) load_checkpoint() (duo_ai.algorithms.ppo.PPOAlgorithm method) (duo_ai.algorithms.PPOAlgorithm method) load_path (duo_ai.policies.always.AlwaysPolicyConfig attribute) (duo_ai.policies.logit.LogitPolicyConfig attribute) (duo_ai.policies.ppo.PPOPolicyConfig attribute) (duo_ai.policies.pyod.PyODPolicyConfig attribute) (duo_ai.policies.random.RandomPolicyConfig attribute), [1] load_policy() (in module duo_ai) log_action_id (duo_ai.algorithms.ppo.PPOAlgorithmConfig attribute) (duo_ai.algorithms.ppo.PPOTrainSummarizer attribute) (duo_ai.core.evaluator.EvaluationSummarizer attribute) (duo_ai.core.evaluator.EvaluatorConfig attribute) log_freq (duo_ai.algorithms.ppo.PPOAlgorithmConfig attribute) log_probs (duo_ai.algorithms.ppo.PPOBatch attribute) logit_dim (duo_ai.models.ImpalaCoordPPOModel attribute) (duo_ai.models.ImpalaPPOModel attribute) (duo_ai.models.ppo.ImpalaCoordPPOModel attribute) (duo_ai.models.ppo.ImpalaPPOModel attribute) LogitAlgorithm (class in duo_ai.algorithms) (class in duo_ai.algorithms.logit) LogitAlgorithmConfig (class in duo_ai.algorithms.logit) LogitPolicy (class in duo_ai.policies) (class in duo_ai.policies.logit) LogitPolicyConfig (class in duo_ai.policies.logit) logits (duo_ai.models.ppo.PPOModelOutput attribute) M make_algorithm() (in module duo_ai) make_config() (in module duo_ai) make_policy() (in module duo_ai) MasterConfig (class in duo_ai) (class in duo_ai.core.config) max_grad_norm (duo_ai.algorithms.ppo.PPOAlgorithmConfig attribute) max_num_steps (duo_ai.core.evaluator.EvaluatorConfig attribute) method (duo_ai.policies.pyod.PyODPolicyConfig attribute) metric (duo_ai.policies.logit.LogitPolicyConfig attribute) model (duo_ai.policies.ppo.PPOPolicy attribute) (duo_ai.policies.ppo.PPOPolicyConfig attribute) (duo_ai.policies.PPOPolicy attribute) module duo_ai duo_ai.algorithms duo_ai.algorithms.always duo_ai.algorithms.logit duo_ai.algorithms.ppo duo_ai.algorithms.pyod duo_ai.algorithms.random duo_ai.core duo_ai.core.algorithm duo_ai.core.config duo_ai.core.environment duo_ai.core.evaluator duo_ai.core.policy duo_ai.environments duo_ai.models duo_ai.models.impala duo_ai.models.ppo duo_ai.policies duo_ai.policies.always duo_ai.policies.logit duo_ai.policies.ppo duo_ai.policies.pyod duo_ai.policies.random duo_ai.utils duo_ai.utils.evaluation duo_ai.utils.global_variables duo_ai.utils.logging duo_ai.utils.model duo_ai.utils.wandb N name (duo_ai.algorithms.always.AlwaysAlgorithmConfig attribute) (duo_ai.algorithms.logit.LogitAlgorithmConfig attribute) (duo_ai.algorithms.ppo.PPOAlgorithmConfig attribute) (duo_ai.algorithms.pyod.PyODAlgorithmConfig attribute) (duo_ai.algorithms.random.RandomAlgorithmConfig attribute) (duo_ai.core.config.MasterConfig attribute) (duo_ai.MasterConfig attribute) (duo_ai.models.ppo.ImpalaCoordPPOModelConfig attribute) (duo_ai.models.ppo.ImpalaPPOModelConfig attribute) (duo_ai.policies.always.AlwaysPolicyConfig attribute) (duo_ai.policies.logit.LogitPolicyConfig attribute) (duo_ai.policies.ppo.PPOPolicyConfig attribute) (duo_ai.policies.pyod.PyODPolicyConfig attribute) (duo_ai.policies.random.RandomPolicyConfig attribute) new() (duo_ai.algorithms.ppo.TrainBuffer class method) norm_adv (duo_ai.algorithms.ppo.PPOAlgorithmConfig attribute) NOVICE (duo_ai.CoordEnv attribute) novice (duo_ai.CoordEnv attribute) NOVICE (duo_ai.core.CoordEnv attribute) novice (duo_ai.core.CoordEnv attribute) NOVICE (duo_ai.core.environment.CoordEnv attribute) novice (duo_ai.core.environment.CoordEnv attribute) num_envs (duo_ai.CoordEnv property) (duo_ai.core.CoordEnv property) (duo_ai.core.environment.CoordEnv property) num_episodes (duo_ai.core.evaluator.EvaluatorConfig attribute) num_minibatches (duo_ai.algorithms.ppo.PPOAlgorithmConfig attribute) num_rollouts (duo_ai.algorithms.logit.LogitAlgorithmConfig attribute) (duo_ai.algorithms.pyod.PyODAlgorithmConfig attribute) num_steps (duo_ai.algorithms.ppo.PPOAlgorithmConfig attribute) O obs (duo_ai.algorithms.ppo.PPOBatch attribute) observation_space (duo_ai.CoordEnv attribute) (duo_ai.core.CoordEnv attribute) (duo_ai.core.environment.CoordEnv attribute) open_expert (duo_ai.CoordEnv attribute) (duo_ai.core.CoordEnv attribute) (duo_ai.core.environment.CoordEnv attribute) open_novice (duo_ai.CoordEnv attribute) (duo_ai.core.CoordEnv attribute) (duo_ai.core.environment.CoordEnv attribute) orthogonal_init() (in module duo_ai.utils.model) output_dim (duo_ai.models.impala.Impala attribute) overwrite (duo_ai.core.config.MasterConfig attribute) (duo_ai.MasterConfig attribute) P params (duo_ai.policies.logit.LogitPolicy attribute) (duo_ai.policies.LogitPolicy attribute) percentiles (duo_ai.algorithms.logit.LogitAlgorithmConfig attribute) (duo_ai.algorithms.pyod.PyODAlgorithmConfig attribute) Policy (class in duo_ai.core) (class in duo_ai.core.policy) policy (duo_ai.core.config.MasterConfig attribute) (duo_ai.MasterConfig attribute) PPOAlgorithm (class in duo_ai.algorithms) (class in duo_ai.algorithms.ppo) PPOAlgorithmConfig (class in duo_ai.algorithms.ppo) PPOBatch (class in duo_ai.algorithms.ppo) PPOModelOutput (class in duo_ai.models.ppo) PPOPolicy (class in duo_ai.policies) (class in duo_ai.policies.ppo) PPOPolicyConfig (class in duo_ai.policies.ppo) PPOTrainSummarizer (class in duo_ai.algorithms.ppo) prob (duo_ai.policies.random.RandomPolicy attribute) (duo_ai.policies.random.RandomPolicyConfig attribute), [1] (duo_ai.policies.RandomPolicy attribute) probs (duo_ai.algorithms.random.RandomAlgorithmConfig attribute) pyod_config (duo_ai.policies.pyod.PyODPolicyConfig attribute) PyODAlgorithm (class in duo_ai.algorithms) (class in duo_ai.algorithms.pyod) PyODAlgorithmConfig (class in duo_ai.algorithms.pyod) PyODPolicy (class in duo_ai.policies) (class in duo_ai.policies.pyod) PyODPolicyConfig (class in duo_ai.policies.pyod) R random (duo_ai.algorithms.pyod.PyODAlgorithm attribute) (duo_ai.algorithms.PyODAlgorithm attribute) RandomAlgorithm (class in duo_ai.algorithms) (class in duo_ai.algorithms.random) RandomAlgorithmConfig (class in duo_ai.algorithms.random) RandomPolicy (class in duo_ai.policies) (class in duo_ai.policies.random) RandomPolicyConfig (class in duo_ai.policies.random) register_algorithm() (in module duo_ai) register_environment() (in module duo_ai) register_model() (in module duo_ai) register_policy() (in module duo_ai) registry (in module duo_ai.algorithms) (in module duo_ai.environments) (in module duo_ai.models) (in module duo_ai.policies) res1 (duo_ai.models.impala.ImpalaBlock attribute) res2 (duo_ai.models.impala.ImpalaBlock attribute) reset() (duo_ai.CoordEnv method) (duo_ai.core.CoordEnv method) (duo_ai.core.environment.CoordEnv method) (duo_ai.core.Policy method) (duo_ai.core.policy.Policy method) (duo_ai.policies.always.AlwaysPolicy method) (duo_ai.policies.AlwaysPolicy method) (duo_ai.policies.logit.LogitPolicy method) (duo_ai.policies.LogitPolicy method) (duo_ai.policies.ppo.PPOPolicy method) (duo_ai.policies.PPOPolicy method) (duo_ai.policies.pyod.PyODPolicy method) (duo_ai.policies.PyODPolicy method) (duo_ai.policies.random.RandomPolicy method) (duo_ai.policies.RandomPolicy method) ResidualBlock (class in duo_ai.models.impala) returns (duo_ai.algorithms.ppo.PPOBatch attribute) S save_checkpoint() (duo_ai.algorithms.logit.LogitAlgorithm method) (duo_ai.algorithms.LogitAlgorithm method) (duo_ai.algorithms.ppo.PPOAlgorithm method) (duo_ai.algorithms.PPOAlgorithm method) (duo_ai.algorithms.pyod.PyODAlgorithm method) (duo_ai.algorithms.PyODAlgorithm method) (duo_ai.algorithms.random.RandomAlgorithm method) (duo_ai.algorithms.RandomAlgorithm method) save_freq (duo_ai.algorithms.ppo.PPOAlgorithmConfig attribute) score_temps (duo_ai.algorithms.logit.LogitAlgorithmConfig attribute) seed (duo_ai.core.config.MasterConfig attribute) (duo_ai.MasterConfig attribute) set_costs() (duo_ai.CoordEnv method) (duo_ai.core.CoordEnv method) (duo_ai.core.environment.CoordEnv method) set_global_variable() (in module duo_ai.utils.global_variables) set_params() (duo_ai.core.Policy method) (duo_ai.core.policy.Policy method) (duo_ai.policies.always.AlwaysPolicy method) (duo_ai.policies.AlwaysPolicy method) (duo_ai.policies.logit.LogitPolicy method) (duo_ai.policies.LogitPolicy method) (duo_ai.policies.ppo.PPOPolicy method) (duo_ai.policies.PPOPolicy method) (duo_ai.policies.pyod.PyODPolicy method) (duo_ai.policies.PyODPolicy method) (duo_ai.policies.random.RandomPolicy method) (duo_ai.policies.RandomPolicy method) start_time (duo_ai.utils.logging.ElapsedFormatter attribute), [1] step() (duo_ai.CoordEnv method) (duo_ai.core.CoordEnv method) (duo_ai.core.environment.CoordEnv method) summarize() (duo_ai.algorithms.ppo.PPOTrainSummarizer method) (duo_ai.core.evaluator.EvaluationSummarizer method) switch_agent_cost_per_action (duo_ai.CoordEnv attribute) (duo_ai.core.CoordEnv attribute) (duo_ai.core.environment.CoordEnv attribute) switch_agent_cost_weight (duo_ai.core.environment.CoordinationConfig attribute) T temperature (duo_ai.core.environment.CoordinationConfig attribute) (duo_ai.core.evaluator.EvaluatorConfig attribute) (duo_ai.policies.logit.LogitPolicyConfig attribute) TensorDict (class in duo_ai.algorithms.ppo) test_expert (duo_ai.core.config.MasterConfig attribute) (duo_ai.MasterConfig attribute) test_novice (duo_ai.core.config.MasterConfig attribute) (duo_ai.MasterConfig attribute) threshold (duo_ai.policies.logit.LogitPolicyConfig attribute) (duo_ai.policies.pyod.PyODPolicy attribute) (duo_ai.policies.PyODPolicy attribute) to() (duo_ai.algorithms.ppo.TensorDict method) total_timesteps (duo_ai.algorithms.ppo.PPOAlgorithmConfig attribute) train() (duo_ai.algorithms.always.AlwaysAlgorithm method) (duo_ai.algorithms.AlwaysAlgorithm method) (duo_ai.algorithms.logit.LogitAlgorithm method) (duo_ai.algorithms.LogitAlgorithm method) (duo_ai.algorithms.ppo.PPOAlgorithm method) (duo_ai.algorithms.PPOAlgorithm method) (duo_ai.algorithms.pyod.PyODAlgorithm method) (duo_ai.algorithms.PyODAlgorithm method) (duo_ai.algorithms.random.RandomAlgorithm method) (duo_ai.algorithms.RandomAlgorithm method) (duo_ai.core.Algorithm method) (duo_ai.core.algorithm.Algorithm method) (duo_ai.core.Policy method) (duo_ai.core.policy.Policy method) (duo_ai.policies.always.AlwaysPolicy method) (duo_ai.policies.AlwaysPolicy method) (duo_ai.policies.logit.LogitPolicy method) (duo_ai.policies.LogitPolicy method) (duo_ai.policies.ppo.PPOPolicy method) (duo_ai.policies.PPOPolicy method) (duo_ai.policies.pyod.PyODPolicy method) (duo_ai.policies.PyODPolicy method) (duo_ai.policies.random.RandomPolicy method) (duo_ai.policies.RandomPolicy method) train_expert (duo_ai.core.config.MasterConfig attribute) (duo_ai.MasterConfig attribute) train_novice (duo_ai.core.config.MasterConfig attribute) (duo_ai.MasterConfig attribute) TrainBuffer (class in duo_ai.algorithms.ppo) U update_epochs (duo_ai.algorithms.ppo.PPOAlgorithmConfig attribute) use_wandb (duo_ai.core.config.MasterConfig attribute) (duo_ai.MasterConfig attribute) V value (duo_ai.models.ppo.PPOModelOutput attribute) values (duo_ai.algorithms.ppo.PPOBatch attribute) vf_coef (duo_ai.algorithms.ppo.PPOAlgorithmConfig attribute) W WandbLogger (class in duo_ai.utils.wandb) write() (duo_ai.algorithms.ppo.PPOTrainSummarizer method) (duo_ai.core.evaluator.EvaluationSummarizer method) X xavier_uniform_init() (in module duo_ai.utils.model) Z zeros() (duo_ai.algorithms.ppo.TensorDict class method)