Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/aviralkumar2907/CQL
/ functions
Functions
729 in github.com/aviralkumar2907/CQL
⨍
Functions
729
◇
Types & classes
125
Method
__init__
:param trigger_period: If None or 0, `check` will always return False.
d4rl/rlkit/pythonplusplus.py:395
Method
__init__
( self, fc_input_size, hidden_sizes, deconv_input_width,
d4rl/rlkit/torch/conv_networks.py:134
Method
__init__
(self)
d4rl/rlkit/torch/torch_rl_algorithm.py:34
Method
__init__
(self, features, center=True, scale=False, eps=1e-6)
d4rl/rlkit/torch/modules.py:24
Method
__init__
( self, *args, obs_normalizer: TorchFixedNormalizer = None, **
d4rl/rlkit/torch/networks.py:96
Method
__init__
(self, *args, **kwargs)
d4rl/rlkit/torch/networks.py:122
Method
__init__
(self, images, should_normalize=True)
d4rl/rlkit/torch/data.py:11
Method
__init__
(self, data_source)
d4rl/rlkit/torch/data.py:30
Method
__init__
(self, data_source, weights)
d4rl/rlkit/torch/data.py:51
Method
__init__
:param normal_mean: Mean of the normal distribution :param normal_std: Std of the normal distribution :param epsilon: Numeric
d4rl/rlkit/torch/distributions.py:14
Method
__init__
( self, representation_size, )
d4rl/rlkit/torch/vae/vae_base.py:89
Method
__init__
( self, train_dataset, test_dataset, model, batch_
d4rl/rlkit/torch/vae/vae_trainer.py:110
Method
__init__
:param representation_size: :param conv_args: must be a dictionary specifying the following: kernel_sizes
d4rl/rlkit/torch/vae/conv_vae.py:107
Method
__init__
( self, env, policy, qf1, qf2, target
d4rl/rlkit/torch/sac/cql.py:14
Method
__init__
( self, hidden_sizes, obs_dim, action_dim, std=Non
d4rl/rlkit/torch/sac/policies.py:39
Method
__init__
( self, env, policy, qf1, qf2, target_
d4rl/rlkit/torch/sac/sac.py:14
Method
__init__
( self, qf, target_qf, policy, target_policy,
d4rl/rlkit/torch/ddpg/ddpg.py:17
Method
__init__
( self, policy, qf1, qf2, target_qf1,
d4rl/rlkit/torch/td3/td3.py:18
Method
__init__
(self, base_trainer: TorchTrainer)
d4rl/rlkit/torch/her/her.py:7
Method
__init__
( self, vae, vae_trainer, *base_args, vae_save_per
d4rl/rlkit/torch/skewfit/online_vae_algorithm.py:18
Method
__init__
( self, qf, target_qf, learning_rate=1e-3, soft_ta
d4rl/rlkit/torch/dqn/dqn.py:14
Method
__init__
( self, max_replay_buffer_size, observation_dim, action_dim, env_info_
d4rl/rlkit/data_management/simple_replay_buffer.py:10
Method
__init__
:param max_replay_buffer_size: :param env:
d4rl/rlkit/data_management/env_replay_buffer.py:9
Method
__init__
( self, *args, **kwargs )
d4rl/rlkit/data_management/shared_obs_dict_replay_buffer.py:25
Method
__init__
(self)
d4rl/rlkit/data_management/path_builder.py:34
Method
__init__
( self, vae, *args, decoded_obs_key='image_observation',
d4rl/rlkit/data_management/online_vae_replay_buffer.py:18
Method
__init__
( self, size, eps=1e-8, default_clip_range=np.inf,
d4rl/rlkit/data_management/normalizer.py:8
Method
__init__
(self, *args, **kwargs)
d4rl/rlkit/data_management/normalizer.py:68
Method
__init__
( self, size, default_clip_range=np.inf, mean=0, s
d4rl/rlkit/data_management/normalizer.py:82
Method
__init__
( self, max_size, env, fraction_goals_rollout_goals=1.0,
d4rl/rlkit/data_management/obs_dict_replay_buffer.py:23
Method
__init__
( self, goal_sampling_mode, env: VAEWrappedEnv, policy,
d4rl/rlkit/samplers/data_collector/vae_env.py:6
Method
__init__
( self, env, policy, max_num_epoch_paths_saved=None,
d4rl/rlkit/samplers/data_collector/step_collector.py:11
Method
__init__
( self, env, policy, max_num_epoch_paths_saved=None,
d4rl/rlkit/samplers/data_collector/step_collector.py:124
Method
__init__
( self, env, policy, max_num_epoch_paths_saved=None,
d4rl/rlkit/samplers/data_collector/path_collector.py:9
Method
__init__
( self, env, max_num_epoch_paths_saved=None, render=False, render_kwar
d4rl/rlkit/samplers/data_collector/path_collector.py:99
Method
__init__
( self, env, policy, max_num_epoch_paths_saved=None,
d4rl/rlkit/samplers/data_collector/path_collector.py:172
Method
__init__
(self)
d4rl/rlkit/core/logging.py:24
Method
__init__
(self, *args, **kwargs)
d4rl/rlkit/core/serializable.py:13
Method
__init__
( self, trainer, exploration_env, evaluation_env,
d4rl/rlkit/core/online_rl_algorithm.py:13
Method
__init__
( self, trainer, exploration_env, evaluation_env,
d4rl/rlkit/core/rl_algorithm.py:25
Method
__init__
( self, trainer, exploration_env, evaluation_env,
d4rl/rlkit/core/batch_rl_algorithm.py:42
Method
__init__
(self, action_space)
d4rl/rlkit/policies/simple.py:9
Method
__init__
(self, qf)
d4rl/rlkit/policies/argmax.py:12
Method
__init__
( self, action_space, mu=0, theta=0.15, max_sigma=
d4rl/rlkit/exploration_strategies/ou_strategy.py:18
Method
__init__
(self, action_space, max_sigma=1.0, min_sigma=None, decay_period=1000000)
d4rl/rlkit/exploration_strategies/gaussian_strategy.py:11
Method
__init__
(self, action_space, epsilon, max_sigma=1.0, min_sigma=None, decay_period=1000000)
d4rl/rlkit/exploration_strategies/gaussian_and_epsilon_strategy.py:12
Method
__init__
( self, exploration_strategy: ExplorationStrategy, policy, )
d4rl/rlkit/exploration_strategies/base.py:29
Method
__init__
(self, action_space, prob_random_action=0.1)
d4rl/rlkit/exploration_strategies/epsilon_greedy.py:10
Method
__init__
(self, use_low_gear_ratio=True)
d4rl/rlkit/envs/ant.py:7
Method
__init__
( self, model_path, frame_skip=1, model_path_is_local=True,
d4rl/rlkit/envs/mujoco_env.py:19
Method
__init__
(self, env, **kwargs)
d4rl/rlkit/envs/mujoco_image_env.py:138
Method
__init__
(self, wrapped_env, history_len)
d4rl/rlkit/envs/wrappers.py:60
Method
__init__
(self, wrapped_env, num_bins)
d4rl/rlkit/envs/wrappers.py:96
Method
__init__
( self, env, reward_scale=1., obs_mean=None, obs_s
d4rl/rlkit/envs/wrappers.py:121
Method
__init__
( self, wrapped_env, vae, vae_input_key_prefix='image', sample_from_tr
d4rl/rlkit/envs/vae_wrapper.py:22
Method
__init__
(self, name)
d4rl/rlkit/util/hyperparameter.py:15
Method
__init__
(self, name)
d4rl/rlkit/util/hyperparameter.py:24
Method
__init__
(self, name, min_value, max_value, *, offset=0)
d4rl/rlkit/util/hyperparameter.py:52
Method
__init__
(self, name, min_value, max_value)
d4rl/rlkit/util/hyperparameter.py:64
Method
__init__
(self, name, min_value, max_value, *, offset=0)
d4rl/rlkit/util/hyperparameter.py:74
Method
__init__
(self, name, min_value, max_value)
d4rl/rlkit/util/hyperparameter.py:88
Method
__init__
(self, name, value)
d4rl/rlkit/util/hyperparameter.py:98
Method
__init__
(self, hyperparameters=None, default_kwargs=None)
d4rl/rlkit/util/hyperparameter.py:111
Method
__init__
:param hyperparameters: A dictionary of the form ``` { 'hp_1': [value1, value2, value3], 'hp_2': [va
d4rl/rlkit/util/hyperparameter.py:156
Method
__init__
(self, sweepers: List[DeterministicHyperparameterSweeper])
d4rl/rlkit/util/hyperparameter.py:206
Method
__init__
(self, value)
d4rl/rlkit/util/ml_util.py:16
Method
__init__
( self, init_value, final_value, ramp_duration, )
d4rl/rlkit/util/ml_util.py:27
Method
__init__
( self, x_values, y_values, )
d4rl/rlkit/util/ml_util.py:58
Method
__init__
Initializes OutOfGraphLoggedPrioritizedReplayBuffer.
atari/batch_rl/baselines/replay_memory/logged_prioritized_replay_buffer.py:43
Method
__init__
(self, log_dir, *args, **kwargs)
atari/batch_rl/baselines/replay_memory/logged_replay_buffer.py:40
Method
__init__
Initializes the agent and constructs the components of its graph. Args: sess: tf.Session, for executing ops. num_actions: int, number
atari/batch_rl/baselines/agents/dqn_agent.py:32
Method
__init__
This maintains all the DQN default argument values.
atari/batch_rl/baselines/agents/random_agent.py:32
Method
__init__
Initializes the agent and constructs the components of its graph. Args: sess: tf.Session, for executing ops. num_actions: int, number
atari/batch_rl/baselines/agents/quantile_agent.py:32
Method
__init__
Creates the layers used calculating return distributions. Args: num_actions: number of actions. num_heads: number of Q-heads. t
atari/batch_rl/multi_head/atari_helpers.py:124
Method
__init__
Creates the layers used for calculating Q-values. Args: num_actions: number of actions. name: used to create scope for network parame
atari/batch_rl/multi_head/atari_helpers.py:257
Method
__init__
Creates the networks used calculating multiple Q-values. Args: num_actions: number of actions. num_networks: number of separate Q-net
atari/batch_rl/multi_head/atari_helpers.py:328
Method
__init__
Initializes the agent and constructs the components of its graph. Args: sess: tf.Session, for executing ops. num_actions: int, number
atari/batch_rl/multi_head/multi_head_dqn_agent.py:30
Method
__init__
Initializes the agent and constructs the Graph. Args: sess: A `tf.Session` object for running associated ops. num_actions: Int, numbe
atari/batch_rl/multi_head/quantile_agent.py:37
Method
__init__
Initializes the agent and constructs the components of its graph. Args: sess: tf.Session, for executing ops. num_actions: int, number
atari/batch_rl/multi_head/multi_network_dqn_agent.py:32
Method
__init__
Initializes WrappedFixedReplayBuffer.
atari/batch_rl/fixed_replay/replay_memory/fixed_replay_buffer.py:214
Method
__init__
Initializes the agent and constructs the components of its graph. Args: sess: tf.Session, for executing ops. num_actions: int, number
atari/batch_rl/fixed_replay/agents/multi_head_dqn_agent.py:33
Method
__init__
Initializes the agent and constructs the components of its graph. Args: sess: tf.Session, for executing ops. num_actions: int, number
atari/batch_rl/fixed_replay/agents/dqn_agent.py:35
Method
__init__
Initializes the agent and constructs the components of its graph. Args: sess: tf.Session, for executing ops. num_actions: int, number
atari/batch_rl/fixed_replay/agents/quantile_agent.py:34
Method
__init__
Initializes the agent and constructs the components of its graph. Args: sess: tf.Session, for executing ops. num_actions: int, number
atari/batch_rl/fixed_replay/agents/rainbow_agent.py:34
Method
__init__
Initializes the agent and constructs the components of its graph. Args: sess: tf.Session, for executing ops. num_actions: int, number
atari/batch_rl/fixed_replay/agents/multi_network_dqn_agent.py:30
Method
__iter__
(self)
d4rl/rlkit/torch/data.py:34
Method
__iter__
(self)
d4rl/rlkit/torch/data.py:70
Method
__len__
(self)
d4rl/rlkit/torch/data.py:18
Method
__len__
(self)
d4rl/rlkit/torch/data.py:45
Method
__len__
(self)
d4rl/rlkit/torch/data.py:81
Method
__len__
(self)
d4rl/rlkit/data_management/path_builder.py:52
Method
__next__
(self)
d4rl/rlkit/torch/data.py:37
Method
__next__
(self)
d4rl/rlkit/torch/data.py:73
Method
__str__
(self)
d4rl/rlkit/envs/wrappers.py:55
Method
__str__
(self)
d4rl/rlkit/envs/wrappers.py:167
Method
_build_networks
(self)
atari/batch_rl/multi_head/multi_network_dqn_agent.py:143
Method
_build_replay_buffer
Creates the replay buffer used by the agent. Args: use_staging: bool, if True, uses a staging area to prefetch data for faster trai
atari/batch_rl/baselines/agents/dqn_agent.py:50
Method
_build_replay_buffer
Creates the replay buffer used by the agent. Args: use_staging: bool, if True, uses a staging area to prefetch data for faster trai
atari/batch_rl/baselines/agents/quantile_agent.py:49
Method
_build_replay_buffer
Creates the replay buffer used by the agent.
atari/batch_rl/fixed_replay/agents/multi_head_dqn_agent.py:74
Method
_build_replay_buffer
Creates the replay buffer used by the agent.
atari/batch_rl/fixed_replay/agents/dqn_agent.py:83
← previous
next →
301–400 of 729, ranked by callers