SYMBOL INDEX (153 symbols across 15 files)

FILE: envs/dclaw.py
  class BaseDClawTurn (line 46) | class BaseDClawTurn(BaseDClawObjectEnv, metaclass=abc.ABCMeta):
    method __init__ (line 49) | def __init__(self,
    method _reset (line 79) | def _reset(self):
    method _step (line 86) | def _step(self, action: np.ndarray):
    method get_obs_dict (line 92) | def get_obs_dict(self) -> Dict[str, np.ndarray]:
    method get_reward_dict (line 116) | def get_reward_dict(
    method get_score_dict (line 125) | def get_score_dict(
    method get_done (line 133) | def get_done(
  class DClawTurnRandom (line 143) | class DClawTurnRandom(BaseDClawTurn):
    method _reset (line 146) | def _reset(self):
  class DClawTurnRandomDynamics (line 154) | class DClawTurnRandomDynamics(DClawTurnRandom):
    method __init__ (line 160) | def __init__(self,
    method _reset (line 171) | def _reset(self):

FILE: envs/dkitty_redesign.py
  class BaseDKittyWalk (line 45) | class BaseDKittyWalk(BaseDKittyUprightEnv, metaclass=abc.ABCMeta):
    method __init__ (line 48) | def __init__(
    method _reset (line 111) | def _reset(self):
    method _step (line 122) | def _step(self, action: np.ndarray):
    method get_obs_dict (line 137) | def get_obs_dict(self) -> Dict[str, np.ndarray]:
    method get_reward_dict (line 163) | def get_reward_dict(
    method get_score_dict (line 172) | def get_score_dict(
  class DKittyRandomDynamics (line 181) | class DKittyRandomDynamics(BaseDKittyWalk):
    method __init__ (line 184) | def __init__(self, *args, randomize_hfield=0.0, **kwargs):
    method _reset (line 191) | def _reset(self):

FILE: envs/gym_mujoco/ant.py
  function q_inv (line 25) | def q_inv(a):
  function q_mult (line 29) | def q_mult(a, b):  # multiply two quaternion
  class AntEnv (line 37) | class AntEnv(mujoco_env.MujocoEnv, utils.EzPickle):
    method __init__ (line 39) | def __init__(self,
    method compute_reward (line 65) | def compute_reward(self, ob, next_ob, action=None):
    method step (line 91) | def step(self, a):
    method _get_obs (line 127) | def _get_obs(self):
    method reset_model (line 160) | def reset_model(self):
    method viewer_setup (line 171) | def viewer_setup(self):
    method get_ori (line 174) | def get_ori(self):
    method body_com_indices (line 182) | def body_com_indices(self):
    method body_comvel_indices (line 186) | def body_comvel_indices(self):

FILE: envs/gym_mujoco/half_cheetah.py
  class HalfCheetahEnv (line 26) | class HalfCheetahEnv(mujoco_env.MujocoEnv, utils.EzPickle):
    method __init__ (line 28) | def __init__(self,
    method step (line 48) | def step(self, action):
    method _get_obs (line 72) | def _get_obs(self):
    method reset_model (line 81) | def reset_model(self):
    method viewer_setup (line 88) | def viewer_setup(self):

FILE: envs/gym_mujoco/humanoid.py
  function mass_center (line 26) | def mass_center(sim):
  class HumanoidEnv (line 33) | class HumanoidEnv(mujoco_env.MujocoEnv, utils.EzPickle):
    method __init__ (line 35) | def __init__(self,
    method _get_obs (line 58) | def _get_obs(self):
    method compute_reward (line 71) | def compute_reward(self, ob, next_ob, action=None):
    method step (line 100) | def step(self, a):
    method reset_model (line 136) | def reset_model(self):
    method viewer_setup (line 154) | def viewer_setup(self):

FILE: envs/gym_mujoco/point_mass.py
  class PointMassEnv (line 28) | class PointMassEnv(mujoco_env.MujocoEnv, utils.EzPickle):
    method __init__ (line 30) | def __init__(self,
    method step (line 57) | def step(self, action):
    method _get_obs (line 85) | def _get_obs(self):
    method reset_model (line 93) | def reset_model(self):
    method set_qpos (line 104) | def set_qpos(self, state):
    method viewer_setup (line 108) | def viewer_setup(self):

FILE: envs/hand_block.py
  class HandBlockCustomEnv (line 24) | class HandBlockCustomEnv(ManipulateEnv):
    method __init__ (line 25) | def __init__(self,
    method _get_viewer (line 49) | def _get_viewer(self, mode):
    method _viewer_setup (line 60) | def _viewer_setup(self):
    method step (line 69) | def step(self, action):
    method render (line 82) | def render(self, mode='human', width=500, height=500):

FILE: envs/skill_wrapper.py
  class SkillWrapper (line 24) | class SkillWrapper(Wrapper):
    method __init__ (line 26) | def __init__(
    method _remake_time_step (line 56) | def _remake_time_step(self, cur_obs):
    method _set_skill (line 65) | def _set_skill(self):
    method reset (line 80) | def reset(self):
    method step (line 86) | def step(self, action):
    method close (line 95) | def close(self):

FILE: envs/video_wrapper.py
  class VideoWrapper (line 25) | class VideoWrapper(Wrapper):
    method __init__ (line 27) | def __init__(self, env, base_path, base_name=None, new_video_every_res...
    method reset (line 44) | def reset(self):
    method step (line 59) | def step(self, action):
    method close (line 63) | def close(self):

FILE: lib/py_tf_policy.py
  class PyTFPolicy (line 32) | class PyTFPolicy(py_policy.Base, session_utils.SessionUser):
    method __init__ (line 41) | def __init__(self, policy, batch_size=None, seed=None):
    method _construct (line 73) | def _construct(self, batch_size, graph):
    method initialize (line 103) | def initialize(self, batch_size, graph=None):
    method save (line 115) | def save(self, policy_dir=None, graph=None):
    method restore (line 130) | def restore(self, policy_dir, graph=None, assert_consumed=True):
    method _build_from_time_step (line 166) | def _build_from_time_step(self, time_step):
    method _get_initial_state (line 178) | def _get_initial_state(self, batch_size):
    method _action (line 188) | def _action(self, time_step, policy_state):
    method log_prob (line 223) | def log_prob(self, time_step, action_step, policy_state=None):

FILE: lib/py_uniform_replay_buffer.py
  class PyUniformReplayBuffer (line 39) | class PyUniformReplayBuffer(replay_buffer.ReplayBuffer):
    method __init__ (line 49) | def __init__(self, data_spec, capacity):
    method _encoded_data_spec (line 73) | def _encoded_data_spec(self):
    method _encode (line 77) | def _encode(self, item):
    method _decode (line 81) | def _decode(self, item):
    method _on_delete (line 85) | def _on_delete(self, encoded_item):
    method size (line 90) | def size(self):
    method _add_batch (line 93) | def _add_batch(self, items):
    method _get_next (line 111) | def _get_next(self,
    method _as_dataset (line 155) | def _as_dataset(self, sample_batch_size=None, num_steps=None,
    method _gather_all (line 193) | def _gather_all(self):
    method _clear (line 200) | def _clear(self):
    method gather_all_transitions (line 204) | def gather_all_transitions(self):

FILE: unsupervised_skill_learning/dads_agent.py
  class DADSAgent (line 36) | class DADSAgent(sac_agent.SacAgent):
    method __init__ (line 38) | def __init__(self,
    method compute_dads_reward (line 89) | def compute_dads_reward(self, input_obs, cur_skill, target_obs):
    method get_experience_placeholder (line 148) | def get_experience_placeholder(self):
    method build_agent_graph (line 163) | def build_agent_graph(self):
    method build_skill_dynamics_graph (line 170) | def build_skill_dynamics_graph(self):
    method create_savers (line 176) | def create_savers(self):
    method set_sessions (line 180) | def set_sessions(self, initialize_or_restore_skill_dynamics, session=N...
    method save_variables (line 189) | def save_variables(self, global_step):
    method _get_dict (line 192) | def _get_dict(self, trajectories, batch_size=-1):
    method train_loop (line 207) | def train_loop(self,
    method skill_dynamics (line 243) | def skill_dynamics(self):

FILE: unsupervised_skill_learning/dads_off.py
  function _normal_projection_net (line 226) | def _normal_projection_net(action_spec, init_means_output_factor=0.1):
  function get_environment (line 235) | def get_environment(env_name='point_mass'):
  function hide_coords (line 298) | def hide_coords(time_step):
  function relabel_skill (line 307) | def relabel_skill(trajectory_sample,
  function process_observation (line 444) | def process_observation(observation):
  function collect_experience (line 555) | def collect_experience(py_env,
  function run_on_env (line 611) | def run_on_env(env,
  function eval_loop (line 680) | def eval_loop(eval_dir,
  function eval_planning (line 829) | def eval_planning(env,
  function eval_mppi (line 893) | def eval_mppi(
  function main (line 1078) | def main(_):

FILE: unsupervised_skill_learning/skill_discriminator.py
  class SkillDiscriminator (line 28) | class SkillDiscriminator:
    method __init__ (line 30) | def __init__(
    method _get_distributions (line 73) | def _get_distributions(self, out):
    method _default_graph (line 121) | def _default_graph(self, timesteps):
    method _get_dict (line 133) | def _get_dict(self,
    method make_placeholders (line 161) | def make_placeholders(self):
    method set_session (line 176) | def set_session(self, session=None, initialize_or_restore_variables=Fa...
    method build_graph (line 200) | def build_graph(self,
    method increase_prob_op (line 235) | def increase_prob_op(self, learning_rate=3e-4):
    method decrease_prob_op (line 244) | def decrease_prob_op(self, learning_rate=3e-4):
    method train (line 254) | def train(self,
    method get_log_probs (line 279) | def get_log_probs(self, timesteps, skills, next_timesteps=None):
    method create_saver (line 290) | def create_saver(self, save_prefix):
    method save_variables (line 302) | def save_variables(self, global_step):
    method restore_variables (line 311) | def restore_variables(self):

FILE: unsupervised_skill_learning/skill_dynamics.py
  class SkillDynamics (line 28) | class SkillDynamics:
    method __init__ (line 30) | def __init__(
    method _get_distribution (line 77) | def _get_distribution(self, out):
    method _graph_with_separate_skill_pipe (line 129) | def _graph_with_separate_skill_pipe(self, timesteps, actions):
    method _default_graph (line 164) | def _default_graph(self, timesteps, actions):
    method _get_dict (line 176) | def _get_dict(self,
    method _get_run_dict (line 213) | def _get_run_dict(self, input_data, input_actions):
    method make_placeholders (line 223) | def make_placeholders(self):
    method set_session (line 240) | def set_session(self, session=None, initialize_or_restore_variables=Fa...
    method build_graph (line 264) | def build_graph(self,
    method increase_prob_op (line 307) | def increase_prob_op(self, learning_rate=3e-4, weights=None):
    method decrease_prob_op (line 328) | def decrease_prob_op(self, learning_rate=3e-4, weights=None):
    method create_saver (line 346) | def create_saver(self, save_prefix):
    method save_variables (line 359) | def save_variables(self, global_step):
    method restore_variables (line 368) | def restore_variables(self):
    method train (line 373) | def train(self,
    method get_log_prob (line 400) | def get_log_prob(self, timesteps, actions, next_timesteps):
    method predict_state (line 409) | def predict_state(self, timesteps, actions):