SYMBOL INDEX (356 symbols across 54 files)

FILE: docs/conf.py
  class Mock (line 31) | class Mock(MagicMock):
    method __getattr__ (line 33) | def __getattr__(cls, name):
  function setup (line 240) | def setup(app):

FILE: spinup/algos/pytorch/ddpg/core.py
  function combined_shape (line 8) | def combined_shape(length, shape=None):
  function mlp (line 13) | def mlp(sizes, activation, output_activation=nn.Identity):
  function count_vars (line 20) | def count_vars(module):
  class MLPActor (line 23) | class MLPActor(nn.Module):
    method __init__ (line 25) | def __init__(self, obs_dim, act_dim, hidden_sizes, activation, act_lim...
    method forward (line 31) | def forward(self, obs):
  class MLPQFunction (line 35) | class MLPQFunction(nn.Module):
    method __init__ (line 37) | def __init__(self, obs_dim, act_dim, hidden_sizes, activation):
    method forward (line 41) | def forward(self, obs, act):
  class MLPActorCritic (line 45) | class MLPActorCritic(nn.Module):
    method __init__ (line 47) | def __init__(self, observation_space, action_space, hidden_sizes=(256,...
    method act (line 59) | def act(self, obs):

FILE: spinup/algos/pytorch/ddpg/ddpg.py
  class ReplayBuffer (line 11) | class ReplayBuffer:
    method __init__ (line 16) | def __init__(self, obs_dim, act_dim, size):
    method store (line 24) | def store(self, obs, act, rew, next_obs, done):
    method sample_batch (line 33) | def sample_batch(self, batch_size=32):
  function ddpg (line 44) | def ddpg(env_fn, actor_critic=core.MLPActorCritic, ac_kwargs=dict(), see...

FILE: spinup/algos/pytorch/ppo/core.py
  function combined_shape (line 11) | def combined_shape(length, shape=None):
  function mlp (line 17) | def mlp(sizes, activation, output_activation=nn.Identity):
  function count_vars (line 25) | def count_vars(module):
  function discount_cumsum (line 29) | def discount_cumsum(x, discount):
  class Actor (line 47) | class Actor(nn.Module):
    method _distribution (line 49) | def _distribution(self, obs):
    method _log_prob_from_distribution (line 52) | def _log_prob_from_distribution(self, pi, act):
    method forward (line 55) | def forward(self, obs, act=None):
  class MLPCategoricalActor (line 66) | class MLPCategoricalActor(Actor):
    method __init__ (line 68) | def __init__(self, obs_dim, act_dim, hidden_sizes, activation):
    method _distribution (line 72) | def _distribution(self, obs):
    method _log_prob_from_distribution (line 76) | def _log_prob_from_distribution(self, pi, act):
  class MLPGaussianActor (line 80) | class MLPGaussianActor(Actor):
    method __init__ (line 82) | def __init__(self, obs_dim, act_dim, hidden_sizes, activation):
    method _distribution (line 88) | def _distribution(self, obs):
    method _log_prob_from_distribution (line 93) | def _log_prob_from_distribution(self, pi, act):
  class MLPCritic (line 97) | class MLPCritic(nn.Module):
    method __init__ (line 99) | def __init__(self, obs_dim, hidden_sizes, activation):
    method forward (line 103) | def forward(self, obs):
  class MLPActorCritic (line 108) | class MLPActorCritic(nn.Module):
    method __init__ (line 111) | def __init__(self, observation_space, action_space,
    method step (line 126) | def step(self, obs):
    method act (line 134) | def act(self, obs):

FILE: spinup/algos/pytorch/ppo/ppo.py
  class PPOBuffer (line 12) | class PPOBuffer:
    method __init__ (line 19) | def __init__(self, obs_dim, act_dim, size, gamma=0.99, lam=0.95):
    method store (line 30) | def store(self, obs, act, rew, val, logp):
    method finish_path (line 42) | def finish_path(self, last_val=0):
    method get (line 71) | def get(self):
  function ppo (line 88) | def ppo(env_fn, actor_critic=core.MLPActorCritic, ac_kwargs=dict(), seed=0,

FILE: spinup/algos/pytorch/sac/core.py
  function combined_shape (line 10) | def combined_shape(length, shape=None):
  function mlp (line 15) | def mlp(sizes, activation, output_activation=nn.Identity):
  function count_vars (line 22) | def count_vars(module):
  class SquashedGaussianMLPActor (line 29) | class SquashedGaussianMLPActor(nn.Module):
    method __init__ (line 31) | def __init__(self, obs_dim, act_dim, hidden_sizes, activation, act_lim...
    method forward (line 38) | def forward(self, obs, deterministic=False, with_logprob=True):
  class MLPQFunction (line 70) | class MLPQFunction(nn.Module):
    method __init__ (line 72) | def __init__(self, obs_dim, act_dim, hidden_sizes, activation):
    method forward (line 76) | def forward(self, obs, act):
  class MLPActorCritic (line 80) | class MLPActorCritic(nn.Module):
    method __init__ (line 82) | def __init__(self, observation_space, action_space, hidden_sizes=(256,...
    method act (line 95) | def act(self, obs, deterministic=False):

FILE: spinup/algos/pytorch/sac/sac.py
  class ReplayBuffer (line 12) | class ReplayBuffer:
    method __init__ (line 17) | def __init__(self, obs_dim, act_dim, size):
    method store (line 25) | def store(self, obs, act, rew, next_obs, done):
    method sample_batch (line 34) | def sample_batch(self, batch_size=32):
  function sac (line 45) | def sac(env_fn, actor_critic=core.MLPActorCritic, ac_kwargs=dict(), seed=0,

FILE: spinup/algos/pytorch/td3/core.py
  function combined_shape (line 8) | def combined_shape(length, shape=None):
  function mlp (line 13) | def mlp(sizes, activation, output_activation=nn.Identity):
  function count_vars (line 20) | def count_vars(module):
  class MLPActor (line 23) | class MLPActor(nn.Module):
    method __init__ (line 25) | def __init__(self, obs_dim, act_dim, hidden_sizes, activation, act_lim...
    method forward (line 31) | def forward(self, obs):
  class MLPQFunction (line 35) | class MLPQFunction(nn.Module):
    method __init__ (line 37) | def __init__(self, obs_dim, act_dim, hidden_sizes, activation):
    method forward (line 41) | def forward(self, obs, act):
  class MLPActorCritic (line 45) | class MLPActorCritic(nn.Module):
    method __init__ (line 47) | def __init__(self, observation_space, action_space, hidden_sizes=(256,...
    method act (line 60) | def act(self, obs):

FILE: spinup/algos/pytorch/td3/td3.py
  class ReplayBuffer (line 12) | class ReplayBuffer:
    method __init__ (line 17) | def __init__(self, obs_dim, act_dim, size):
    method store (line 25) | def store(self, obs, act, rew, next_obs, done):
    method sample_batch (line 34) | def sample_batch(self, batch_size=32):
  function td3 (line 45) | def td3(env_fn, actor_critic=core.MLPActorCritic, ac_kwargs=dict(), seed=0,

FILE: spinup/algos/pytorch/trpo/trpo.py
  function trpo (line 1) | def trpo(*args, **kwargs):

FILE: spinup/algos/pytorch/vpg/core.py
  function combined_shape (line 11) | def combined_shape(length, shape=None):
  function mlp (line 17) | def mlp(sizes, activation, output_activation=nn.Identity):
  function count_vars (line 25) | def count_vars(module):
  function discount_cumsum (line 29) | def discount_cumsum(x, discount):
  class Actor (line 47) | class Actor(nn.Module):
    method _distribution (line 49) | def _distribution(self, obs):
    method _log_prob_from_distribution (line 52) | def _log_prob_from_distribution(self, pi, act):
    method forward (line 55) | def forward(self, obs, act=None):
  class MLPCategoricalActor (line 66) | class MLPCategoricalActor(Actor):
    method __init__ (line 68) | def __init__(self, obs_dim, act_dim, hidden_sizes, activation):
    method _distribution (line 72) | def _distribution(self, obs):
    method _log_prob_from_distribution (line 76) | def _log_prob_from_distribution(self, pi, act):
  class MLPGaussianActor (line 80) | class MLPGaussianActor(Actor):
    method __init__ (line 82) | def __init__(self, obs_dim, act_dim, hidden_sizes, activation):
    method _distribution (line 88) | def _distribution(self, obs):
    method _log_prob_from_distribution (line 93) | def _log_prob_from_distribution(self, pi, act):
  class MLPCritic (line 97) | class MLPCritic(nn.Module):
    method __init__ (line 99) | def __init__(self, obs_dim, hidden_sizes, activation):
    method forward (line 103) | def forward(self, obs):
  class MLPActorCritic (line 108) | class MLPActorCritic(nn.Module):
    method __init__ (line 111) | def __init__(self, observation_space, action_space,
    method step (line 126) | def step(self, obs):
    method act (line 134) | def act(self, obs):

FILE: spinup/algos/pytorch/vpg/vpg.py
  class VPGBuffer (line 12) | class VPGBuffer:
    method __init__ (line 19) | def __init__(self, obs_dim, act_dim, size, gamma=0.99, lam=0.95):
    method store (line 30) | def store(self, obs, act, rew, val, logp):
    method finish_path (line 42) | def finish_path(self, last_val=0):
    method get (line 71) | def get(self):
  function vpg (line 88) | def vpg(env_fn, actor_critic=core.MLPActorCritic, ac_kwargs=dict(),  see...

FILE: spinup/algos/tf1/ddpg/core.py
  function placeholder (line 5) | def placeholder(dim=None):
  function placeholders (line 8) | def placeholders(*args):
  function mlp (line 11) | def mlp(x, hidden_sizes=(32,), activation=tf.tanh, output_activation=None):
  function get_vars (line 16) | def get_vars(scope):
  function count_vars (line 19) | def count_vars(scope):
  function mlp_actor_critic (line 26) | def mlp_actor_critic(x, a, hidden_sizes=(256,256), activation=tf.nn.relu,

FILE: spinup/algos/tf1/ddpg/ddpg.py
  class ReplayBuffer (line 10) | class ReplayBuffer:
    method __init__ (line 15) | def __init__(self, obs_dim, act_dim, size):
    method store (line 23) | def store(self, obs, act, rew, next_obs, done):
    method sample_batch (line 32) | def sample_batch(self, batch_size=32):
  function ddpg (line 42) | def ddpg(env_fn, actor_critic=core.mlp_actor_critic, ac_kwargs=dict(), s...

FILE: spinup/algos/tf1/ppo/core.py
  function combined_shape (line 8) | def combined_shape(length, shape=None):
  function placeholder (line 13) | def placeholder(dim=None):
  function placeholders (line 16) | def placeholders(*args):
  function placeholder_from_space (line 19) | def placeholder_from_space(space):
  function placeholders_from_spaces (line 26) | def placeholders_from_spaces(*args):
  function mlp (line 29) | def mlp(x, hidden_sizes=(32,), activation=tf.tanh, output_activation=None):
  function get_vars (line 34) | def get_vars(scope=''):
  function count_vars (line 37) | def count_vars(scope=''):
  function gaussian_likelihood (line 41) | def gaussian_likelihood(x, mu, log_std):
  function discount_cumsum (line 45) | def discount_cumsum(x, discount):
  function mlp_categorical_policy (line 67) | def mlp_categorical_policy(x, a, hidden_sizes, activation, output_activa...
  function mlp_gaussian_policy (line 77) | def mlp_gaussian_policy(x, a, hidden_sizes, activation, output_activatio...
  function mlp_actor_critic (line 91) | def mlp_actor_critic(x, a, hidden_sizes=(64,64), activation=tf.tanh,

FILE: spinup/algos/tf1/ppo/ppo.py
  class PPOBuffer (line 11) | class PPOBuffer:
    method __init__ (line 18) | def __init__(self, obs_dim, act_dim, size, gamma=0.99, lam=0.95):
    method store (line 29) | def store(self, obs, act, rew, val, logp):
    method finish_path (line 41) | def finish_path(self, last_val=0):
    method get (line 70) | def get(self):
  function ppo (line 86) | def ppo(env_fn, actor_critic=core.mlp_actor_critic, ac_kwargs=dict(), se...

FILE: spinup/algos/tf1/sac/core.py
  function placeholder (line 6) | def placeholder(dim=None):
  function placeholders (line 9) | def placeholders(*args):
  function mlp (line 12) | def mlp(x, hidden_sizes=(32,), activation=tf.tanh, output_activation=None):
  function get_vars (line 17) | def get_vars(scope):
  function count_vars (line 20) | def count_vars(scope):
  function gaussian_likelihood (line 24) | def gaussian_likelihood(x, mu, log_std):
  function mlp_gaussian_policy (line 36) | def mlp_gaussian_policy(x, a, hidden_sizes, activation, output_activation):
  function apply_squashing_func (line 48) | def apply_squashing_func(mu, pi, logp_pi):
  function mlp_actor_critic (line 64) | def mlp_actor_critic(x, a, hidden_sizes=(256,256), activation=tf.nn.relu,

FILE: spinup/algos/tf1/sac/sac.py
  class ReplayBuffer (line 10) | class ReplayBuffer:
    method __init__ (line 15) | def __init__(self, obs_dim, act_dim, size):
    method store (line 23) | def store(self, obs, act, rew, next_obs, done):
    method sample_batch (line 32) | def sample_batch(self, batch_size=32):
  function sac (line 42) | def sac(env_fn, actor_critic=core.mlp_actor_critic, ac_kwargs=dict(), se...

FILE: spinup/algos/tf1/td3/core.py
  function placeholder (line 5) | def placeholder(dim=None):
  function placeholders (line 8) | def placeholders(*args):
  function mlp (line 11) | def mlp(x, hidden_sizes=(32,), activation=tf.tanh, output_activation=None):
  function get_vars (line 16) | def get_vars(scope):
  function count_vars (line 19) | def count_vars(scope):
  function mlp_actor_critic (line 26) | def mlp_actor_critic(x, a, hidden_sizes=(256,256), activation=tf.nn.relu,

FILE: spinup/algos/tf1/td3/td3.py
  class ReplayBuffer (line 10) | class ReplayBuffer:
    method __init__ (line 15) | def __init__(self, obs_dim, act_dim, size):
    method store (line 23) | def store(self, obs, act, rew, next_obs, done):
    method sample_batch (line 32) | def sample_batch(self, batch_size=32):
  function td3 (line 42) | def td3(env_fn, actor_critic=core.mlp_actor_critic, ac_kwargs=dict(), se...

FILE: spinup/algos/tf1/trpo/core.py
  function combined_shape (line 8) | def combined_shape(length, shape=None):
  function keys_as_sorted_list (line 13) | def keys_as_sorted_list(dict):
  function values_as_sorted_list (line 16) | def values_as_sorted_list(dict):
  function placeholder (line 19) | def placeholder(dim=None):
  function placeholders (line 22) | def placeholders(*args):
  function placeholder_from_space (line 25) | def placeholder_from_space(space):
  function placeholders_from_spaces (line 32) | def placeholders_from_spaces(*args):
  function mlp (line 35) | def mlp(x, hidden_sizes=(32,), activation=tf.tanh, output_activation=None):
  function get_vars (line 40) | def get_vars(scope=''):
  function count_vars (line 43) | def count_vars(scope=''):
  function gaussian_likelihood (line 47) | def gaussian_likelihood(x, mu, log_std):
  function diagonal_gaussian_kl (line 51) | def diagonal_gaussian_kl(mu0, log_std0, mu1, log_std1):
  function categorical_kl (line 62) | def categorical_kl(logp0, logp1):
  function flat_concat (line 70) | def flat_concat(xs):
  function flat_grad (line 73) | def flat_grad(f, params):
  function hessian_vector_product (line 76) | def hessian_vector_product(f, params):
  function assign_params_from_flat (line 82) | def assign_params_from_flat(x, params):
  function discount_cumsum (line 88) | def discount_cumsum(x, discount):
  function mlp_categorical_policy (line 109) | def mlp_categorical_policy(x, a, hidden_sizes, activation, output_activa...
  function mlp_gaussian_policy (line 126) | def mlp_gaussian_policy(x, a, hidden_sizes, activation, output_activatio...
  function mlp_actor_critic (line 147) | def mlp_actor_critic(x, a, hidden_sizes=(64,64), activation=tf.tanh,

FILE: spinup/algos/tf1/trpo/trpo.py
  class GAEBuffer (line 13) | class GAEBuffer:
    method __init__ (line 20) | def __init__(self, obs_dim, act_dim, size, info_shapes, gamma=0.99, la...
    method store (line 33) | def store(self, obs, act, rew, val, logp, info):
    method finish_path (line 47) | def finish_path(self, last_val=0):
    method get (line 76) | def get(self):
  function trpo (line 92) | def trpo(env_fn, actor_critic=core.mlp_actor_critic, ac_kwargs=dict(), s...

FILE: spinup/algos/tf1/vpg/core.py
  function combined_shape (line 8) | def combined_shape(length, shape=None):
  function placeholder (line 13) | def placeholder(dim=None):
  function placeholders (line 16) | def placeholders(*args):
  function placeholder_from_space (line 19) | def placeholder_from_space(space):
  function placeholders_from_spaces (line 26) | def placeholders_from_spaces(*args):
  function mlp (line 29) | def mlp(x, hidden_sizes=(32,), activation=tf.tanh, output_activation=None):
  function get_vars (line 34) | def get_vars(scope=''):
  function count_vars (line 37) | def count_vars(scope=''):
  function gaussian_likelihood (line 41) | def gaussian_likelihood(x, mu, log_std):
  function discount_cumsum (line 45) | def discount_cumsum(x, discount):
  function mlp_categorical_policy (line 67) | def mlp_categorical_policy(x, a, hidden_sizes, activation, output_activa...
  function mlp_gaussian_policy (line 77) | def mlp_gaussian_policy(x, a, hidden_sizes, activation, output_activatio...
  function mlp_actor_critic (line 91) | def mlp_actor_critic(x, a, hidden_sizes=(64,64), activation=tf.tanh,

FILE: spinup/algos/tf1/vpg/vpg.py
  class VPGBuffer (line 11) | class VPGBuffer:
    method __init__ (line 18) | def __init__(self, obs_dim, act_dim, size, gamma=0.99, lam=0.95):
    method store (line 29) | def store(self, obs, act, rew, val, logp):
    method finish_path (line 41) | def finish_path(self, last_val=0):
    method get (line 70) | def get(self):
  function vpg (line 86) | def vpg(env_fn, actor_critic=core.mlp_actor_critic, ac_kwargs=dict(), se...

FILE: spinup/examples/pytorch/pg_math/1_simple_pg.py
  function mlp (line 9) | def mlp(sizes, activation=nn.Tanh, output_activation=nn.Identity):
  function train (line 17) | def train(env_name='CartPole-v0', hidden_sizes=[32], lr=1e-2,

FILE: spinup/examples/pytorch/pg_math/2_rtg_pg.py
  function mlp (line 9) | def mlp(sizes, activation=nn.Tanh, output_activation=nn.Identity):
  function reward_to_go (line 17) | def reward_to_go(rews):
  function train (line 24) | def train(env_name='CartPole-v0', hidden_sizes=[32], lr=1e-2,

FILE: spinup/examples/tf1/pg_math/1_simple_pg.py
  function mlp (line 6) | def mlp(x, sizes, activation=tf.tanh, output_activation=None):
  function train (line 12) | def train(env_name='CartPole-v0', hidden_sizes=[32], lr=1e-2,

FILE: spinup/examples/tf1/pg_math/2_rtg_pg.py
  function mlp (line 6) | def mlp(x, sizes, activation=tf.tanh, output_activation=None):
  function reward_to_go (line 12) | def reward_to_go(rews):
  function train (line 19) | def train(env_name='CartPole-v0', hidden_sizes=[32], lr=1e-2,

FILE: spinup/examples/tf1/train_mnist.py
  function mlp (line 7) | def mlp(x, hidden_sizes=(32,), activation=tf.tanh, output_activation=None):
  function train_mnist (line 14) | def train_mnist(steps_per_epoch=100, epochs=5,

FILE: spinup/exercises/common.py
  function print_result (line 1) | def print_result(correct=False):

FILE: spinup/exercises/pytorch/problem_set_1/exercise1_1.py
  function gaussian_likelihood (line 16) | def gaussian_likelihood(x, mu, log_std):

FILE: spinup/exercises/pytorch/problem_set_1/exercise1_2.py
  function mlp (line 19) | def mlp(sizes, activation, output_activation=nn.Identity):
  class DiagonalGaussianDistribution (line 43) | class DiagonalGaussianDistribution:
    method __init__ (line 45) | def __init__(self, mu, log_std):
    method sample (line 49) | def sample(self):
    method log_prob (line 63) | def log_prob(self, value):
    method entropy (line 66) | def entropy(self):
  class MLPGaussianActor (line 71) | class MLPGaussianActor(nn.Module):
    method __init__ (line 73) | def __init__(self, obs_dim, act_dim, hidden_sizes, activation):
    method forward (line 93) | def forward(self, obs, act=None):

FILE: spinup/exercises/pytorch/problem_set_1/exercise1_2_auxiliary.py
  function mlp (line 17) | def mlp(sizes, activation, output_activation=nn.Identity):
  class MLPCritic (line 25) | class MLPCritic(nn.Module):
    method __init__ (line 27) | def __init__(self, obs_dim, hidden_sizes, activation):
    method forward (line 31) | def forward(self, obs):
  class ExerciseActorCritic (line 35) | class ExerciseActorCritic(nn.Module):
    method __init__ (line 37) | def __init__(self, observation_space, action_space,
    method step (line 45) | def step(self, obs):
    method act (line 53) | def act(self, obs):

FILE: spinup/exercises/pytorch/problem_set_1/exercise1_3.py
  class ReplayBuffer (line 27) | class ReplayBuffer:
    method __init__ (line 32) | def __init__(self, obs_dim, act_dim, size):
    method store (line 40) | def store(self, obs, act, rew, next_obs, done):
    method sample_batch (line 49) | def sample_batch(self, batch_size=32):
  function td3 (line 60) | def td3(env_fn, actor_critic=core.MLPActorCritic, ac_kwargs=dict(), seed=0,

FILE: spinup/exercises/pytorch/problem_set_1_solutions/exercise1_1_soln.py
  function gaussian_likelihood (line 6) | def gaussian_likelihood(x, mu, log_std):

FILE: spinup/exercises/pytorch/problem_set_1_solutions/exercise1_2_soln.py
  function mlp (line 7) | def mlp(sizes, activation, output_activation=nn.Identity):
  function gaussian_likelihood (line 14) | def gaussian_likelihood(x, mu, log_std):
  class DiagonalGaussianDistribution (line 19) | class DiagonalGaussianDistribution:
    method __init__ (line 21) | def __init__(self, mu, log_std):
    method sample (line 25) | def sample(self):
    method log_prob (line 28) | def log_prob(self, value):
    method entropy (line 31) | def entropy(self):
  class MLPGaussianActor (line 35) | class MLPGaussianActor(nn.Module):
    method __init__ (line 37) | def __init__(self, obs_dim, act_dim, hidden_sizes, activation):
    method forward (line 43) | def forward(self, obs, act=None):

FILE: spinup/exercises/pytorch/problem_set_2/exercise2_2.py
  class BuggedMLPActor (line 24) | class BuggedMLPActor(nn.Module):
    method __init__ (line 26) | def __init__(self, obs_dim, act_dim, hidden_sizes, activation, act_lim...
    method forward (line 32) | def forward(self, obs):
  class BuggedMLPQFunction (line 36) | class BuggedMLPQFunction(nn.Module):
    method __init__ (line 38) | def __init__(self, obs_dim, act_dim, hidden_sizes, activation):
    method forward (line 42) | def forward(self, obs, act):
  class BuggedMLPActorCritic (line 45) | class BuggedMLPActorCritic(nn.Module):
    method __init__ (line 47) | def __init__(self, observation_space, action_space, hidden_sizes=(256,...
    method act (line 59) | def act(self, obs):
  function ddpg_with_actor_critic (line 75) | def ddpg_with_actor_critic(bugged, **kwargs):

FILE: spinup/exercises/tf1/problem_set_1/exercise1_1.py
  function gaussian_likelihood (line 16) | def gaussian_likelihood(x, mu, log_std):

FILE: spinup/exercises/tf1/problem_set_1/exercise1_2.py
  function mlp (line 18) | def mlp(x, hidden_sizes=(32,), activation=tf.tanh, output_activation=None):
  function mlp_gaussian_policy (line 43) | def mlp_gaussian_policy(x, a, hidden_sizes, activation, output_activatio...

FILE: spinup/exercises/tf1/problem_set_1/exercise1_3.py
  class ReplayBuffer (line 25) | class ReplayBuffer:
    method __init__ (line 30) | def __init__(self, obs_dim, act_dim, size):
    method store (line 38) | def store(self, obs, act, rew, next_obs, done):
    method sample_batch (line 47) | def sample_batch(self, batch_size=32):
  function td3 (line 58) | def td3(env_fn, actor_critic=core.mlp_actor_critic, ac_kwargs=dict(), se...

FILE: spinup/exercises/tf1/problem_set_1_solutions/exercise1_1_soln.py
  function gaussian_likelihood (line 6) | def gaussian_likelihood(x, mu, log_std):

FILE: spinup/exercises/tf1/problem_set_1_solutions/exercise1_2_soln.py
  function mlp (line 7) | def mlp(x, hidden_sizes=(32,), activation=tf.tanh, output_activation=None):
  function gaussian_likelihood (line 12) | def gaussian_likelihood(x, mu, log_std):
  function mlp_gaussian_policy (line 16) | def mlp_gaussian_policy(x, a, hidden_sizes, activation, output_activatio...

FILE: spinup/exercises/tf1/problem_set_2/exercise2_2.py
  function bugged_mlp_actor_critic (line 22) | def bugged_mlp_actor_critic(x, a, hidden_sizes=(400,300), activation=tf....
  function ddpg_with_actor_critic (line 46) | def ddpg_with_actor_critic(bugged, **kwargs):

FILE: spinup/run.py
  function add_with_backends (line 35) | def add_with_backends(algo_list):
  function friendly_err (line 43) | def friendly_err(err_msg):
  function parse_and_execute_grid_search (line 48) | def parse_and_execute_grid_search(cmd, args):

FILE: spinup/utils/logx.py
  function colorize (line 31) | def colorize(string, color, bold=False, highlight=False):
  function restore_tf_graph (line 44) | def restore_tf_graph(sess, fpath):
  class Logger (line 71) | class Logger:
    method __init__ (line 79) | def __init__(self, output_dir=None, output_fname='progress.txt', exp_n...
    method log (line 115) | def log(self, msg, color='green'):
    method log_tabular (line 120) | def log_tabular(self, key, val):
    method save_config (line 136) | def save_config(self, config):
    method save_state (line 162) | def save_state(self, state_dict, itr=None):
    method setup_tf_saver (line 194) | def setup_tf_saver(self, sess, inputs, outputs):
    method _tf_simple_save (line 216) | def _tf_simple_save(self, itr=None):
    method setup_pytorch_saver (line 234) | def setup_pytorch_saver(self, what_to_save):
    method _pytorch_simple_save (line 250) | def _pytorch_simple_save(self, itr=None):
    method dump_tabular (line 275) | def dump_tabular(self):
  class EpochLogger (line 303) | class EpochLogger(Logger):
    method __init__ (line 328) | def __init__(self, *args, **kwargs):
    method store (line 332) | def store(self, **kwargs):
    method log_tabular (line 344) | def log_tabular(self, key, val=None, with_min_and_max=False, average_o...
    method get_stats (line 377) | def get_stats(self, key):

FILE: spinup/utils/mpi_pytorch.py
  function setup_pytorch_for_mpi (line 8) | def setup_pytorch_for_mpi():
  function mpi_avg_grads (line 20) | def mpi_avg_grads(module):
  function sync_params (line 29) | def sync_params(module):

FILE: spinup/utils/mpi_tf.py
  function flat_concat (line 7) | def flat_concat(xs):
  function assign_params_from_flat (line 10) | def assign_params_from_flat(x, params):
  function sync_params (line 16) | def sync_params(params):
  function sync_all_params (line 24) | def sync_all_params():
  class MpiAdamOptimizer (line 29) | class MpiAdamOptimizer(tf.train.AdamOptimizer):
    method __init__ (line 41) | def __init__(self, **kwargs):
    method compute_gradients (line 45) | def compute_gradients(self, loss, var_list, **kwargs):
    method apply_gradients (line 71) | def apply_gradients(self, grads_and_vars, global_step=None, name=None):

FILE: spinup/utils/mpi_tools.py
  function mpi_fork (line 6) | def mpi_fork(n, bind_to_core=False):
  function msg (line 39) | def msg(m, string=''):
  function proc_id (line 42) | def proc_id():
  function allreduce (line 46) | def allreduce(*args, **kwargs):
  function num_procs (line 49) | def num_procs():
  function broadcast (line 53) | def broadcast(x, root=0):
  function mpi_op (line 56) | def mpi_op(x, op):
  function mpi_sum (line 63) | def mpi_sum(x):
  function mpi_avg (line 66) | def mpi_avg(x):
  function mpi_statistics_scalar (line 70) | def mpi_statistics_scalar(x, with_min_and_max=False):

FILE: spinup/utils/plot.py
  function plot_data (line 15) | def plot_data(data, xaxis='Epoch', value="AverageEpRet", condition="Cond...
  function get_datasets (line 61) | def get_datasets(logdir, condition=None):
  function get_all_datasets (line 103) | def get_all_datasets(all_logdirs, legend=None, select=None, exclude=None):
  function make_plots (line 154) | def make_plots(all_logdirs, legend=None, xaxis=None, values=None, count=...
  function main (line 166) | def main():

FILE: spinup/utils/run_utils.py
  function setup_logger_kwargs (line 25) | def setup_logger_kwargs(exp_name, seed=None, data_dir=None, datestamp=Fa...
  function call_experiment (line 89) | def call_experiment(exp_name, thunk, seed=0, num_cpu=1, data_dir=None,
  function all_bools (line 214) | def all_bools(vals):
  function valid_str (line 217) | def valid_str(v):
  class ExperimentGrid (line 240) | class ExperimentGrid:
    method __init__ (line 245) | def __init__(self, name=''):
    method name (line 252) | def name(self, _name):
    method print (line 256) | def print(self):
    method _default_shorthand (line 295) | def _default_shorthand(self, key):
    method add (line 306) | def add(self, key, vals, shorthand=None, in_name=False):
    method variant_name (line 339) | def variant_name(self, variant):
    method _variants (line 394) | def _variants(self, keys, vals):
    method variants (line 412) | def variants(self):
    method run (line 480) | def run(self, thunk, num_cpu=1, data_dir=None, datestamp=False):
  function test_eg (line 549) | def test_eg():

FILE: spinup/utils/serialization_utils.py
  function convert_json (line 3) | def convert_json(obj):
  function is_json_serializable (line 28) | def is_json_serializable(v):

FILE: spinup/utils/test_policy.py
  function load_policy_and_env (line 11) | def load_policy_and_env(fpath, itr='last', deterministic=False):
  function load_tf_policy (line 67) | def load_tf_policy(fpath, itr, deterministic=False):
  function load_pytorch_policy (line 92) | def load_pytorch_policy(fpath, itr, deterministic=False):
  function run_policy (line 110) | def run_policy(env, get_action, max_ep_len=None, num_episodes=100, rende...

FILE: spinup/version.py
  function get_version (line 5) | def get_version():

FILE: test/test_ppo.py
  class TestPPO (line 12) | class TestPPO(unittest.TestCase):
    method test_cartpole (line 13) | def test_cartpole(self):