MCPcopy Create free account

hub / github.com/2019ChenGong/Offline_RL_Poisoner / functions

Functions1,427 in github.com/2019ChenGong/Offline_RL_Poisoner

⨍ Functions 1,427◇ Types & classes 176↳ Endpoints 37
↓ 4 callersFunctionevaluate_on_environment_test
Returns scorer function of evaluation on environment. This function returns scorer function, which is suitable to the standard scikit-learn s
d3rlpy/metrics/scorer.py:491
↓ 4 callersFunctionget_action_size_from_env
(env: gym.Env)
d3rlpy/online/utility.py:7
↓ 4 callersFunctionget_pendulum
Returns pendulum dataset and environment. The dataset is automatically downloaded to ``d3rlpy_data/pendulum.h5`` if it does not exist. A
d3rlpy/datasets.py:63
↓ 4 callersFunctionget_state_dict
(impl: Any)
d3rlpy/torch_utility.py:97
↓ 4 callersMethodlog_probs
(self, x: torch.Tensor)
d3rlpy/models/torch/policies.py:302
↓ 4 callersFunctionmap_location
(device: str)
d3rlpy/torch_utility.py:120
↓ 4 callersFunctionplot
(score_list, label)
mujoco/plot.py:205
↓ 4 callersMethodpredict_value
(self, x, action, with_std=False)
tests/metrics/test_scorer.py:42
↓ 4 callersMethodpredict_with_variance
( self, x: torch.Tensor, action: torch.Tensor )
d3rlpy/models/torch/dynamics.py:102
↓ 4 callersFunctionregister_encoder_factory
Registers encoder factory class. Args: cls: encoder factory class inheriting ``EncoderFactory``.
d3rlpy/models/encoders.py:410
↓ 4 callersFunctionregister_q_func_factory
Registers Q function factory class. Args: cls: Q function factory class inheriting ``QFunctionFactory``.
d3rlpy/models/q_functions.py:327
↓ 4 callersMethodsample_with_log_prob
( self, x: torch.Tensor )
d3rlpy/models/torch/policies.py:27
↓ 4 callersMethodsave_policy
(self, fname)
tests/algos/algo_test.py:31
↓ 4 callersFunctionsoft_sync
(targ_model: nn.Module, model: nn.Module, tau: float)
d3rlpy/torch_utility.py:27
↓ 4 callersMethodstep
(self, action)
tests/dummy_env.py:21
↓ 4 callersMethodtransform
(self, x: torch.Tensor)
d3rlpy/preprocessing/scalers.py:214
↓ 4 callersMethodtransform_numpy
Returns transformed rewards in numpy array. Args: reward: reward. Returns: transformed reward.
d3rlpy/preprocessing/reward_scalers.py:62
↓ 4 callersMethodupdate_imitator
(self, batch: TorchMiniBatch)
d3rlpy/algos/torch/bcq_impl.py:150
↓ 3 callersMethod__init__
(self, env: gym.Env, is_eval: bool = False)
d3rlpy/envs/wrappers.py:260
↓ 3 callersMethod__init__
( self, encoder_encoder: EncoderWithAction, decoder_encoder: EncoderWithAction,
d3rlpy/models/torch/imitators.py:26
↓ 3 callersMethod__init__
( self, observation_shape: Sequence[int], filters: Optional[List[Sequence[int]]] = Non
d3rlpy/models/torch/encoders.py:79
↓ 3 callersMethod__init__
(self, encoder: Encoder, action_size: int)
d3rlpy/models/torch/policies.py:250
↓ 3 callersMethod_compute_mmd_loss
(self, obs_t: torch.Tensor)
d3rlpy/algos/torch/bear_impl.py:189
↓ 3 callersMethod_compute_quantiles
( self, h: torch.Tensor, taus: torch.Tensor )
d3rlpy/models/torch/q_functions/iqn_q_function.py:83
↓ 3 callersMethod_compute_quantiles
( self, h: torch.Tensor, taus: torch.Tensor )
d3rlpy/models/torch/q_functions/iqn_q_function.py:177
↓ 3 callersMethod_get_linear_input_size
(self)
d3rlpy/models/torch/encoders.py:129
↓ 3 callersFunction_get_params_json_path
(path: str)
d3rlpy/cli.py:197
↓ 3 callersMethod_make_taus
(self, h: torch.Tensor)
d3rlpy/models/torch/q_functions/iqn_q_function.py:76
↓ 3 callersMethod_make_taus
(self, h: torch.Tensor)
d3rlpy/models/torch/q_functions/iqn_q_function.py:170
↓ 3 callersMethod_process_observation_shape
( self, observation_shape: Sequence[int] )
d3rlpy/base.py:727
↓ 3 callersFunction_reduce_quantile_ensemble
( y: torch.Tensor, reduction: str = "min", dim: int = 0, lam: float = 0.75 )
d3rlpy/models/torch/q_functions/ensemble_q_function.py:47
↓ 3 callersMethod_repeat_observation
(self, x: torch.Tensor)
d3rlpy/algos/torch/bcq_impl.py:163
↓ 3 callersMethod_sample_repeated_action
( self, repeated_x: torch.Tensor, target: bool = False )
d3rlpy/algos/torch/bcq_impl.py:169
↓ 3 callersMethodadd_generated_transitions
(self, transitions: List[Transition])
d3rlpy/iterators/base.py:84
↓ 3 callersFunctionbase_tester
(model, impl, observation_shape, action_size=2)
tests/base_test.py:11
↓ 3 callersMethodbest_action
(self, x: torch.Tensor)
d3rlpy/models/torch/policies.py:42
↓ 3 callersFunctioncheck_if_same_dict
(a, b)
tests/test_torch_utility.py:163
↓ 3 callersMethodcompute_log_probs_with_logits
( self, x: torch.Tensor )
d3rlpy/models/torch/imitators.py:150
↓ 3 callersMethodcompute_stats
( self, x: torch.Tensor, action: torch.Tensor )
d3rlpy/models/torch/dynamics.py:83
↓ 3 callersMethodcompute_target
( self, x: torch.Tensor, action: Optional[torch.Tensor] = None, reduction: str
d3rlpy/models/torch/q_functions/ensemble_q_function.py:153
↓ 3 callersFunctioncreate_action_scaler
Returns registered action scaler object. Args: name: regsitered scaler type name. kwargs: scaler arguments. Returns:
d3rlpy/preprocessing/action_scalers.py:245
↓ 3 callersFunctioncreate_deterministic_residual_policy
( observation_shape: Sequence[int], action_size: int, scale: float, encoder_factory: EncoderFa
d3rlpy/models/builders.py:81
↓ 3 callersFunctioncreate_discrete_imitator
( observation_shape: Sequence[int], action_size: int, beta: float, encoder_factory: EncoderFac
d3rlpy/models/builders.py:142
↓ 3 callersFunctioncreate_encoder_factory
Returns registered encoder factory object. Args: name: regsitered encoder factory type name. kwargs: encoder arguments. Retu
d3rlpy/models/encoders.py:422
↓ 3 callersFunctioncreate_reward_scaler
(name: str, **kwargs: Any)
d3rlpy/preprocessing/reward_scalers.py:505
↓ 3 callersFunctioncreate_scaler
Returns registered scaler object. Args: name: regsitered scaler type name. kwargs: scaler arguments. Returns: scaler
d3rlpy/preprocessing/scalers.py:391
↓ 3 callersFunctiondisable_parallel
()
d3rlpy/context.py:19
↓ 3 callersMethodencode
(self, x: torch.Tensor, action: torch.Tensor)
d3rlpy/models/torch/imitators.py:63
↓ 3 callersMethodeval
Returns stacked observation. Returns: numpy.ndarray: stacked observation.
d3rlpy/preprocessing/stack.py:115
↓ 3 callersMethodfit
(self, episodes)
tests/algos/algo_test.py:53
↓ 3 callersMethodforward
(self, x: torch.Tensor)
d3rlpy/models/torch/q_functions/mean_q_function.py:23
↓ 3 callersFunctionfreeze
(impl: Any)
d3rlpy/torch_utility.py:81
↓ 3 callersMethodget_action_type
Returns action type (continuous or discrete). Returns: action type.
d3rlpy/base.py:839
↓ 3 callersMethodget_params
Returns the all attributes. This method returns the all attributes including ones in subclasses. Some of scikit-learn utilities will
d3rlpy/base.py:266
↓ 3 callersMethodload_model
(self, fname)
tests/algos/algo_test.py:28
↓ 3 callersFunctionmain
(args)
carla/cql-carla-lane-v0.py:8
↓ 3 callersMethodonnx_safe_sample_n
(self, x: torch.Tensor, n: int)
d3rlpy/models/torch/policies.py:219
↓ 3 callersFunctionpoison_carla
(dataset)
carla/poisoned_dataset.py:8
↓ 3 callersMethodpredict
(self, x: Union[np.ndarray, List[Any]])
d3rlpy/online/explorers.py:11
↓ 3 callersMethodpredict
(self, x, action, with_variance=False)
tests/metrics/test_scorer.py:454
↓ 3 callersMethodpredict_best_action
(self, x)
tests/algos/algo_test.py:34
↓ 3 callersMethodpredict_with_variance
( self, x: torch.Tensor, action: torch.Tensor, variance_type: str = "data",
d3rlpy/models/torch/dynamics.py:173
↓ 3 callersFunctionprint_f1_score
(tp, fn, tn, fp)
mujoco/backdoor_detection.py:135
↓ 3 callersFunctionref_quantile_huber_loss
(a, b, taus, n_quantiles)
tests/models/torch/model_test.py:40
↓ 3 callersFunctionregister_scaler
Registers scaler class. Args: cls: scaler class inheriting ``Scaler``.
d3rlpy/preprocessing/scalers.py:379
↓ 3 callersMethodsample
Returns action with noise injection. Args: algo: algorithm. x: observation. Returns: action with
d3rlpy/online/explorers.py:128
↓ 3 callersMethodsample_action
(self, x)
tests/algos/algo_test.py:40
↓ 3 callersMethodsample_n_with_log_prob
( self, x: torch.Tensor, n: int )
d3rlpy/models/torch/policies.py:36
↓ 3 callersMethodsample_n_without_squash
(self, x: torch.Tensor, n: int)
d3rlpy/models/torch/imitators.py:117
↓ 3 callersMethodsave_model
(self, fname)
tests/algos/algo_test.py:25
↓ 3 callersFunctionset_state_dict
(impl: Any, chkpt: Dict[str, Any])
d3rlpy/torch_utility.py:106
↓ 3 callersFunctionsync_optimizer_state
(targ_optim: Optimizer, optim: Optimizer)
d3rlpy/torch_utility.py:44
↓ 3 callersMethodtransform
(self, action: torch.Tensor)
d3rlpy/preprocessing/action_scalers.py:188
↓ 3 callersMethodupdate_target
(self)
d3rlpy/algos/torch/dqn_impl.py:146
↓ 2 callersMethod__init__
( self, *, learning_rate: float = 1e-3, optim_factory: OptimizerFactory = Adam
d3rlpy/algos/bc.py:115
↓ 2 callersMethod__init__
( self, observation_shape: Sequence[int], action_size: int, learning_rate: flo
d3rlpy/algos/torch/bc_impl.py:123
↓ 2 callersMethod__init__
( self, momentum: float = 0, dampening: float = 0, weight_decay: float = 0,
d3rlpy/models/optimizers.py:89
↓ 2 callersFunction_assert_action_space
(algo: LearnableBase, env: gym.Env)
d3rlpy/algos/base.py:19
↓ 2 callersMethod_compute_conservative_loss
( self, obs_t: torch.Tensor, act_t: torch.Tensor, obs_tp1: torch.Tensor )
d3rlpy/algos/torch/cql_impl.py:196
↓ 2 callersFunction_compute_ensemble_variance
( observations: torch.Tensor, rewards: torch.Tensor, variances: torch.Tensor, variance_type: s
d3rlpy/models/torch/dynamics.py:14
↓ 2 callersMethod_compute_logstd
(self, h: torch.Tensor)
d3rlpy/models/torch/policies.py:157
↓ 2 callersMethod_compute_random_is_values
(self, obs: torch.Tensor)
d3rlpy/algos/torch/cql_impl.py:173
↓ 2 callersMethod_compute_target
( self, x: torch.Tensor, action: Optional[torch.Tensor] = None, reduction: str
d3rlpy/models/torch/q_functions/ensemble_q_function.py:108
↓ 2 callersFunction_exec_to_create_env
(code: str)
d3rlpy/cli.py:249
↓ 2 callersMethod_fc_encode
(self, x: torch.Tensor)
d3rlpy/models/torch/encoders.py:325
↓ 2 callersFunction_gaussian_likelihood
( x: torch.Tensor, mu: torch.Tensor, logstd: torch.Tensor )
d3rlpy/models/torch/dynamics.py:38
↓ 2 callersMethod_get_last_conv_shape
(self)
d3rlpy/models/torch/encoders.py:134
↓ 2 callersMethod_get_obs
(self)
d3rlpy/envs/wrappers.py:230
↓ 2 callersFunction_make_taus
( h: torch.Tensor, n_quantiles: int, training: bool )
d3rlpy/models/torch/q_functions/iqn_q_function.py:16
↓ 2 callersMethod_predict_best_action
(self, x: torch.Tensor)
d3rlpy/algos/torch/dqn_impl.py:139
↓ 2 callersMethod_predict_best_action
(self, x: torch.Tensor)
d3rlpy/algos/torch/base.py:66
↓ 2 callersMethod_predict_value
( self, repeated_x: torch.Tensor, action: torch.Tensor, )
d3rlpy/algos/torch/bcq_impl.py:189
↓ 2 callersMethod_sample_rollout_action
(self, observations: np.ndarray)
d3rlpy/algos/utility.py:82
↓ 2 callersFunction_setup_algo
(algo: AlgoProtocol, env: gym.Env)
d3rlpy/online/iterators.py:76
↓ 2 callersMethodappend_episode
Append Episode object to buffer. Args: episode: episode.
d3rlpy/online/buffers.py:55
↓ 2 callersFunctionbase_update_tester
(model, observation_shape, action_size, discrete=False)
tests/base_test.py:139
↓ 2 callersMethodbuild
(self)
d3rlpy/ope/torch/fqe_impl.py:79
↓ 2 callersMethodbuild
(self)
d3rlpy/dynamics/torch/probabilistic_ensemble_dynamics_impl.py:63
↓ 2 callersMethodbuild
(self)
tests/algos/algo_test.py:22
↓ 2 callersMethodbuild_with_env
Instantiate implementation object with OpenAI Gym object. Args: env: gym-like environment.
d3rlpy/base.py:714
← previousnext →101–200 of 1,427, ranked by callers