TF2RL
Contents:
tf2rl package
TF2RL
»
Index
Index
_
|
A
|
B
|
C
|
D
|
E
|
F
|
G
|
H
|
I
|
L
|
M
|
N
|
O
|
P
|
Q
|
R
|
S
|
T
|
U
|
V
|
W
_
__init__() (tf2rl.algos.bi_res_ddpg.BiResDDPG method)
(tf2rl.algos.categorical_dqn.CategoricalDQN method)
(tf2rl.algos.categorical_dqn.QFunc method)
(tf2rl.algos.curl_sac.CURL method)
(tf2rl.algos.d2rl_sac.D2RLSAC method)
(tf2rl.algos.ddpg.Actor method)
(tf2rl.algos.ddpg.Critic method)
(tf2rl.algos.ddpg.DDPG method)
(tf2rl.algos.dqn.DQN method)
(tf2rl.algos.dqn.QFunc method)
(tf2rl.algos.gaifo.Discriminator method)
(tf2rl.algos.gaifo.GAIfO method)
(tf2rl.algos.gail.Discriminator method)
(tf2rl.algos.gail.GAIL method)
(tf2rl.algos.policy_base.IRLPolicy method)
(tf2rl.algos.policy_base.OffPolicyAgent method)
(tf2rl.algos.policy_base.OnPolicyAgent method)
(tf2rl.algos.policy_base.Policy method)
(tf2rl.algos.ppo.PPO method)
(tf2rl.algos.sac.CriticQ method)
(tf2rl.algos.sac.SAC method)
(tf2rl.algos.sac_ae.SACAE method)
(tf2rl.algos.sac_discrete.CriticQ method)
(tf2rl.algos.sac_discrete.SACDiscrete method)
(tf2rl.algos.td3.Critic method)
(tf2rl.algos.td3.TD3 method)
(tf2rl.algos.vail.Discriminator method)
(tf2rl.algos.vail.VAIL method)
(tf2rl.algos.vpg.CriticV method)
(tf2rl.algos.vpg.VPG method)
(tf2rl.envs.atari_wrapper.ClipRewardEnv method)
(tf2rl.envs.atari_wrapper.EpisodicLifeEnv method)
(tf2rl.envs.atari_wrapper.FireResetEnv method)
(tf2rl.envs.atari_wrapper.FrameStack method)
(tf2rl.envs.atari_wrapper.LazyFrames method)
(tf2rl.envs.atari_wrapper.MaxAndSkipEnv method)
(tf2rl.envs.atari_wrapper.NdarrayFrames method)
(tf2rl.envs.atari_wrapper.NoopResetEnv method)
(tf2rl.envs.atari_wrapper.ProcessFrame84 method)
(tf2rl.envs.atari_wrapper.ScaledFloatFrame method)
(tf2rl.envs.atari_wrapper.WarpFrame method)
(tf2rl.envs.dmc_wrapper.DMCWrapper method)
(tf2rl.envs.frame_stack_wrapper.FrameStack method)
(tf2rl.envs.multi_thread_env.MultiThreadEnv method)
(tf2rl.envs.normalizer.EmpiricalNormalizer method)
(tf2rl.experiments.irl_trainer.IRLTrainer method)
(tf2rl.experiments.me_trpo_trainer.MeTrpoTrainer method)
(tf2rl.experiments.mpc_trainer.DynamicsModel method)
(tf2rl.experiments.mpc_trainer.MPCTrainer method)
(tf2rl.experiments.mpc_trainer.RandomPolicy method)
(tf2rl.experiments.on_policy_trainer.OnPolicyTrainer method)
(tf2rl.experiments.trainer.Trainer method)
(tf2rl.misc.normalizer.Normalizer method)
(tf2rl.misc.normalizer.NormalizerNumpy method)
(tf2rl.networks.atari_model.AtariBaseModel method)
(tf2rl.networks.atari_model.AtariCategoricalActor method)
(tf2rl.networks.atari_model.AtariCategoricalActorCritic method)
(tf2rl.networks.atari_model.AtariQFunc method)
(tf2rl.networks.dmc_model.Decoder method)
(tf2rl.networks.dmc_model.Encoder method)
(tf2rl.networks.noisy_dense.NoisyDense method)
(tf2rl.networks.spectral_norm_dense.SNDense method)
(tf2rl.policies.tfp_categorical_actor.CategoricalActor method)
(tf2rl.policies.tfp_categorical_actor.CategoricalActorCritic method)
(tf2rl.policies.tfp_gaussian_actor.GaussianActor method)
(tf2rl.tools.vae.VAE method)
A
Actor (class in tf2rl.algos.ddpg)
apex_argument() (in module tf2rl.algos.apex)
AtariBaseModel (class in tf2rl.networks.atari_model)
AtariCategoricalActor (class in tf2rl.networks.atari_model)
AtariCategoricalActorCritic (class in tf2rl.networks.atari_model)
AtariQFunc (class in tf2rl.networks.atari_model)
B
BiResDDPG (class in tf2rl.algos.bi_res_ddpg)
build() (tf2rl.networks.noisy_dense.NoisyDense method)
(tf2rl.networks.spectral_norm_dense.SNDense method)
C
call() (tf2rl.algos.categorical_dqn.QFunc method)
(tf2rl.algos.d2rl_sac.DenseCriticQ method)
(tf2rl.algos.ddpg.Actor method)
(tf2rl.algos.ddpg.Critic method)
(tf2rl.algos.dqn.QFunc method)
(tf2rl.algos.gail.Discriminator method)
(tf2rl.algos.sac.CriticQ method)
(tf2rl.algos.sac_discrete.CriticQ method)
(tf2rl.algos.td3.Critic method)
(tf2rl.algos.vail.Discriminator method)
(tf2rl.algos.vpg.CriticV method)
(tf2rl.experiments.mpc_trainer.DynamicsModel method)
(tf2rl.networks.atari_model.AtariBaseModel method)
(tf2rl.networks.atari_model.AtariQFunc method)
(tf2rl.networks.dmc_model.Decoder method)
(tf2rl.networks.dmc_model.Encoder method)
(tf2rl.networks.noisy_dense.NoisyDense method)
(tf2rl.networks.spectral_norm_dense.SNDense method)
(tf2rl.policies.tfp_categorical_actor.CategoricalActor method)
(tf2rl.policies.tfp_categorical_actor.CategoricalActorCritic method)
(tf2rl.policies.tfp_gaussian_actor.GaussianActor method)
CategoricalActor (class in tf2rl.policies.tfp_categorical_actor)
CategoricalActorCritic (class in tf2rl.policies.tfp_categorical_actor)
CategoricalDQN (class in tf2rl.algos.categorical_dqn)
center_crop() (in module tf2rl.tools.img_tools)
ClipRewardEnv (class in tf2rl.envs.atari_wrapper)
collect_episodes() (tf2rl.experiments.mpc_trainer.MPCTrainer method)
collect_transitions_real_env() (tf2rl.experiments.me_trpo_trainer.MeTrpoTrainer method)
collect_transitions_sim_env() (tf2rl.experiments.me_trpo_trainer.MeTrpoTrainer method)
compute_apply_gradients() (tf2rl.tools.vae.VAE method)
compute_entropy() (tf2rl.policies.tfp_categorical_actor.CategoricalActor method)
(tf2rl.policies.tfp_gaussian_actor.GaussianActor method)
compute_log_probs() (tf2rl.policies.tfp_categorical_actor.CategoricalActor method)
(tf2rl.policies.tfp_gaussian_actor.GaussianActor method)
compute_loss() (tf2rl.tools.vae.VAE method)
compute_output_shape() (tf2rl.networks.noisy_dense.NoisyDense method)
compute_prob() (tf2rl.policies.tfp_categorical_actor.CategoricalActor method)
compute_reward() (tf2rl.algos.gail.Discriminator method)
(tf2rl.algos.vail.Discriminator method)
compute_spectral_norm() (tf2rl.networks.spectral_norm_dense.SNDense method)
compute_td_error() (tf2rl.algos.bi_res_ddpg.BiResDDPG method)
(tf2rl.algos.categorical_dqn.CategoricalDQN method)
(tf2rl.algos.ddpg.DDPG method)
(tf2rl.algos.dqn.DQN method)
(tf2rl.algos.sac.SAC method)
(tf2rl.algos.sac_ae.SACAE method)
(tf2rl.algos.sac_discrete.SACDiscrete method)
(tf2rl.algos.td3.TD3 method)
Critic (class in tf2rl.algos.ddpg)
(class in tf2rl.algos.td3)
CriticQ (class in tf2rl.algos.sac)
(class in tf2rl.algos.sac_discrete)
CriticV (class in tf2rl.algos.vpg)
CURL (class in tf2rl.algos.curl_sac)
D
D2RLSAC (class in tf2rl.algos.d2rl_sac)
DDPG (class in tf2rl.algos.ddpg)
decode() (tf2rl.tools.vae.VAE method)
Decoder (class in tf2rl.networks.dmc_model)
DenseCriticQ (class in tf2rl.algos.d2rl_sac)
DenseGaussianActor (class in tf2rl.algos.d2rl_sac)
discount_cumsum() (in module tf2rl.misc.discount_cumsum)
Discriminator (class in tf2rl.algos.gaifo)
(class in tf2rl.algos.gail)
(class in tf2rl.algos.vail)
DMCWrapper (class in tf2rl.envs.dmc_wrapper)
DQN (class in tf2rl.algos.dqn)
DynamicsModel (class in tf2rl.experiments.mpc_trainer)
E
EmpiricalNormalizer (class in tf2rl.envs.normalizer)
encode() (tf2rl.tools.vae.VAE method)
Encoder (class in tf2rl.networks.dmc_model)
EpisodicLifeEnv (class in tf2rl.envs.atari_wrapper)
EPS (tf2rl.algos.vail.Discriminator attribute)
(tf2rl.policies.tfp_gaussian_actor.GaussianActor attribute)
evaluate_policy() (tf2rl.experiments.me_trpo_trainer.MeTrpoTrainer method)
(tf2rl.experiments.on_policy_trainer.OnPolicyTrainer method)
(tf2rl.experiments.trainer.Trainer method)
evaluate_policy_continuously() (tf2rl.experiments.trainer.Trainer method)
evaluator() (in module tf2rl.algos.apex)
experience() (tf2rl.envs.normalizer.EmpiricalNormalizer method)
explorer() (in module tf2rl.algos.apex)
F
finish_horizon() (tf2rl.experiments.me_trpo_trainer.MeTrpoTrainer method)
(tf2rl.experiments.on_policy_trainer.OnPolicyTrainer method)
FireResetEnv (class in tf2rl.envs.atari_wrapper)
fit_dynamics() (tf2rl.experiments.mpc_trainer.MPCTrainer method)
frames_to_gif() (in module tf2rl.experiments.utils)
FrameStack (class in tf2rl.envs.atari_wrapper)
(class in tf2rl.envs.frame_stack_wrapper)
G
GAIfO (class in tf2rl.algos.gaifo)
GAIL (class in tf2rl.algos.gail)
GaussianActor (class in tf2rl.policies.tfp_gaussian_actor)
get_act_dim() (in module tf2rl.envs.env_utils)
(in module tf2rl.envs.utils)
get_action() (tf2rl.algos.categorical_dqn.CategoricalDQN method)
(tf2rl.algos.ddpg.DDPG method)
(tf2rl.algos.dqn.DQN method)
(tf2rl.algos.policy_base.Policy method)
(tf2rl.algos.sac.SAC method)
(tf2rl.algos.sac_ae.SACAE method)
(tf2rl.algos.vpg.VPG method)
(tf2rl.experiments.mpc_trainer.RandomPolicy method)
get_action_and_val() (tf2rl.algos.vpg.VPG method)
get_actions() (tf2rl.experiments.mpc_trainer.RandomPolicy method)
get_argument() (tf2rl.algos.bi_res_ddpg.BiResDDPG static method)
(tf2rl.algos.categorical_dqn.CategoricalDQN static method)
(tf2rl.algos.dqn.DQN static method)
(tf2rl.algos.gail.GAIL static method)
(tf2rl.algos.policy_base.OffPolicyAgent static method)
(tf2rl.algos.policy_base.OnPolicyAgent static method)
(tf2rl.algos.policy_base.Policy static method)
(tf2rl.algos.sac.SAC static method)
(tf2rl.algos.sac_ae.SACAE static method)
(tf2rl.algos.sac_discrete.SACDiscrete static method)
(tf2rl.experiments.irl_trainer.IRLTrainer static method)
(tf2rl.experiments.me_trpo_trainer.MeTrpoTrainer static method)
(tf2rl.experiments.mpc_trainer.MPCTrainer static method)
(tf2rl.experiments.trainer.Trainer static method)
get_config() (tf2rl.networks.spectral_norm_dense.SNDense method)
get_default_rb_dict() (in module tf2rl.misc.get_replay_buffer)
get_filenames() (in module tf2rl.experiments.utils)
get_params() (tf2rl.misc.normalizer.NormalizerNumpy method)
get_replay_buffer() (in module tf2rl.misc.get_replay_buffer)
get_space_size() (in module tf2rl.misc.get_replay_buffer)
H
huber_loss() (in module tf2rl.misc.huber_loss)
I
import_tf() (in module tf2rl.algos.apex)
inference() (tf2rl.algos.gaifo.GAIfO method)
(tf2rl.algos.gail.GAIL method)
initialize_logger() (in module tf2rl.misc.initialize_logger)
inverse() (tf2rl.envs.normalizer.EmpiricalNormalizer method)
IRLPolicy (class in tf2rl.algos.policy_base)
IRLTrainer (class in tf2rl.experiments.irl_trainer)
is_atari_env() (in module tf2rl.envs.utils)
is_discrete() (in module tf2rl.envs.utils)
is_mujoco_env() (in module tf2rl.envs.utils)
is_return_code_zero() (in module tf2rl.misc.prepare_output_dir)
is_under_git_control() (in module tf2rl.misc.prepare_output_dir)
L
LazyFrames (class in tf2rl.envs.atari_wrapper)
learner() (in module tf2rl.algos.apex)
load_trajectories() (in module tf2rl.experiments.utils)
log_normal_pdf() (in module tf2rl.tools.vae)
LOG_SIG_CAP_MAX (tf2rl.algos.vail.Discriminator attribute)
LOG_SIG_CAP_MIN (tf2rl.algos.vail.Discriminator attribute)
LOG_STD_CAP_MAX (tf2rl.policies.tfp_gaussian_actor.GaussianActor attribute)
LOG_STD_CAP_MIN (tf2rl.policies.tfp_gaussian_actor.GaussianActor attribute)
M
make() (in module tf2rl.envs.utils)
make_atari() (in module tf2rl.envs.atari_wrapper)
max_action (tf2rl.envs.multi_thread_env.MultiThreadEnv property)
MaxAndSkipEnv (class in tf2rl.envs.atari_wrapper)
mean (tf2rl.envs.normalizer.EmpiricalNormalizer property)
MeTrpoTrainer (class in tf2rl.experiments.me_trpo_trainer)
min_action (tf2rl.envs.multi_thread_env.MultiThreadEnv property)
module
tf2rl
tf2rl.algos
tf2rl.algos.apex
tf2rl.algos.bi_res_ddpg
tf2rl.algos.categorical_dqn
tf2rl.algos.curl_sac
tf2rl.algos.d2rl_sac
tf2rl.algos.ddpg
tf2rl.algos.dqn
tf2rl.algos.gaifo
tf2rl.algos.gail
tf2rl.algos.policy_base
tf2rl.algos.ppo
tf2rl.algos.sac
tf2rl.algos.sac_ae
tf2rl.algos.sac_discrete
tf2rl.algos.td3
tf2rl.algos.vail
tf2rl.algos.vpg
tf2rl.envs
tf2rl.envs.atari_wrapper
tf2rl.envs.dmc_wrapper
tf2rl.envs.env_utils
tf2rl.envs.frame_stack_wrapper
tf2rl.envs.multi_thread_env
tf2rl.envs.normalizer
tf2rl.envs.utils
tf2rl.experiments
tf2rl.experiments.irl_trainer
tf2rl.experiments.me_trpo_trainer
tf2rl.experiments.mpc_trainer
tf2rl.experiments.on_policy_trainer
tf2rl.experiments.trainer
tf2rl.experiments.utils
tf2rl.misc
tf2rl.misc.discount_cumsum
tf2rl.misc.get_replay_buffer
tf2rl.misc.huber_loss
tf2rl.misc.initialize_logger
tf2rl.misc.normalizer
tf2rl.misc.periodic_ops
tf2rl.misc.prepare_output_dir
tf2rl.misc.target_update_ops
tf2rl.networks
tf2rl.networks.atari_model
tf2rl.networks.dmc_model
tf2rl.networks.noisy_dense
tf2rl.networks.spectral_norm_dense
tf2rl.policies
tf2rl.policies.tfp_categorical_actor
tf2rl.policies.tfp_gaussian_actor
tf2rl.tools
tf2rl.tools.img_tools
tf2rl.tools.vae
MPCTrainer (class in tf2rl.experiments.mpc_trainer)
MultiThreadEnv (class in tf2rl.envs.multi_thread_env)
N
n_atoms (tf2rl.algos.categorical_dqn.QFunc property)
NdarrayFrames (class in tf2rl.envs.atari_wrapper)
NoisyDense (class in tf2rl.networks.noisy_dense)
NoopResetEnv (class in tf2rl.envs.atari_wrapper)
normalize() (tf2rl.misc.normalizer.Normalizer method)
(tf2rl.misc.normalizer.NormalizerNumpy method)
Normalizer (class in tf2rl.misc.normalizer)
NormalizerNumpy (class in tf2rl.misc.normalizer)
O
observation() (tf2rl.envs.atari_wrapper.ProcessFrame84 method)
(tf2rl.envs.atari_wrapper.ScaledFloatFrame method)
(tf2rl.envs.atari_wrapper.WarpFrame method)
observe() (tf2rl.misc.normalizer.Normalizer method)
(tf2rl.misc.normalizer.NormalizerNumpy method)
OffPolicyAgent (class in tf2rl.algos.policy_base)
OnPolicyAgent (class in tf2rl.algos.policy_base)
OnPolicyTrainer (class in tf2rl.experiments.on_policy_trainer)
original_env (tf2rl.envs.multi_thread_env.MultiThreadEnv property)
P
periodic_target_update() (in module tf2rl.misc.target_update_ops)
periodically() (in module tf2rl.misc.periodic_ops)
Policy (class in tf2rl.algos.policy_base)
PPO (class in tf2rl.algos.ppo)
predict() (tf2rl.experiments.mpc_trainer.DynamicsModel method)
predict_next_state() (tf2rl.experiments.me_trpo_trainer.MeTrpoTrainer method)
(tf2rl.experiments.mpc_trainer.MPCTrainer method)
prepare_experiment() (in module tf2rl.algos.apex)
prepare_output_dir() (in module tf2rl.misc.prepare_output_dir)
preprocess_img() (in module tf2rl.tools.img_tools)
process() (tf2rl.envs.atari_wrapper.ProcessFrame84 static method)
ProcessFrame84 (class in tf2rl.envs.atari_wrapper)
py_observation() (tf2rl.envs.multi_thread_env.MultiThreadEnv method)
py_reset() (tf2rl.envs.multi_thread_env.MultiThreadEnv method)
py_step() (tf2rl.envs.multi_thread_env.MultiThreadEnv method)
Q
QFunc (class in tf2rl.algos.categorical_dqn)
(class in tf2rl.algos.dqn)
R
random_crop() (in module tf2rl.tools.img_tools)
RandomPolicy (class in tf2rl.experiments.mpc_trainer)
render() (tf2rl.envs.dmc_wrapper.DMCWrapper method)
reparameterize() (tf2rl.tools.vae.VAE method)
reset() (tf2rl.envs.atari_wrapper.EpisodicLifeEnv method)
(tf2rl.envs.atari_wrapper.FireResetEnv method)
(tf2rl.envs.atari_wrapper.FrameStack method)
(tf2rl.envs.atari_wrapper.MaxAndSkipEnv method)
(tf2rl.envs.atari_wrapper.NdarrayFrames method)
(tf2rl.envs.atari_wrapper.NoopResetEnv method)
(tf2rl.envs.frame_stack_wrapper.FrameStack method)
restore_latest_n_traj() (in module tf2rl.experiments.utils)
reward() (tf2rl.envs.atari_wrapper.ClipRewardEnv method)
run() (in module tf2rl.algos.apex)
S
SAC (class in tf2rl.algos.sac)
SACAE (class in tf2rl.algos.sac_ae)
SACDiscrete (class in tf2rl.algos.sac_discrete)
sample() (tf2rl.tools.vae.VAE method)
save_path() (in module tf2rl.experiments.utils)
ScaledFloatFrame (class in tf2rl.envs.atari_wrapper)
set_params() (tf2rl.misc.normalizer.NormalizerNumpy method)
SNDense (class in tf2rl.networks.spectral_norm_dense)
state_dim (tf2rl.envs.multi_thread_env.MultiThreadEnv property)
std (tf2rl.envs.normalizer.EmpiricalNormalizer property)
step() (tf2rl.envs.atari_wrapper.EpisodicLifeEnv method)
(tf2rl.envs.atari_wrapper.FireResetEnv method)
(tf2rl.envs.atari_wrapper.FrameStack method)
(tf2rl.envs.atari_wrapper.MaxAndSkipEnv method)
(tf2rl.envs.atari_wrapper.NdarrayFrames method)
(tf2rl.envs.atari_wrapper.NoopResetEnv method)
(tf2rl.envs.frame_stack_wrapper.FrameStack method)
(tf2rl.envs.multi_thread_env.MultiThreadEnv method)
T
TD3 (class in tf2rl.algos.td3)
tf2rl
module
tf2rl.algos
module
tf2rl.algos.apex
module
tf2rl.algos.bi_res_ddpg
module
tf2rl.algos.categorical_dqn
module
tf2rl.algos.curl_sac
module
tf2rl.algos.d2rl_sac
module
tf2rl.algos.ddpg
module
tf2rl.algos.dqn
module
tf2rl.algos.gaifo
module
tf2rl.algos.gail
module
tf2rl.algos.policy_base
module
tf2rl.algos.ppo
module
tf2rl.algos.sac
module
tf2rl.algos.sac_ae
module
tf2rl.algos.sac_discrete
module
tf2rl.algos.td3
module
tf2rl.algos.vail
module
tf2rl.algos.vpg
module
tf2rl.envs
module
tf2rl.envs.atari_wrapper
module
tf2rl.envs.dmc_wrapper
module
tf2rl.envs.env_utils
module
tf2rl.envs.frame_stack_wrapper
module
tf2rl.envs.multi_thread_env
module
tf2rl.envs.normalizer
module
tf2rl.envs.utils
module
tf2rl.experiments
module
tf2rl.experiments.irl_trainer
module
tf2rl.experiments.me_trpo_trainer
module
tf2rl.experiments.mpc_trainer
module
tf2rl.experiments.on_policy_trainer
module
tf2rl.experiments.trainer
module
tf2rl.experiments.utils
module
tf2rl.misc
module
tf2rl.misc.discount_cumsum
module
tf2rl.misc.get_replay_buffer
module
tf2rl.misc.huber_loss
module
tf2rl.misc.initialize_logger
module
tf2rl.misc.normalizer
module
tf2rl.misc.periodic_ops
module
tf2rl.misc.prepare_output_dir
module
tf2rl.misc.target_update_ops
module
tf2rl.networks
module
tf2rl.networks.atari_model
module
tf2rl.networks.dmc_model
module
tf2rl.networks.noisy_dense
module
tf2rl.networks.spectral_norm_dense
module
tf2rl.policies
module
tf2rl.policies.tfp_categorical_actor
module
tf2rl.policies.tfp_gaussian_actor
module
tf2rl.tools
module
tf2rl.tools.img_tools
module
tf2rl.tools.vae
module
train() (tf2rl.algos.categorical_dqn.CategoricalDQN method)
(tf2rl.algos.curl_sac.CURL method)
(tf2rl.algos.ddpg.DDPG method)
(tf2rl.algos.dqn.DQN method)
(tf2rl.algos.gaifo.GAIfO method)
(tf2rl.algos.gail.GAIL method)
(tf2rl.algos.ppo.PPO method)
(tf2rl.algos.sac.SAC method)
(tf2rl.algos.sac_ae.SACAE method)
(tf2rl.algos.sac_discrete.SACDiscrete method)
(tf2rl.algos.vail.VAIL method)
(tf2rl.algos.vpg.VPG method)
Trainer (class in tf2rl.experiments.trainer)
U
update_policy() (tf2rl.experiments.me_trpo_trainer.MeTrpoTrainer method)
update_target_variables() (in module tf2rl.misc.target_update_ops)
V
VAE (class in tf2rl.tools.vae)
VAIL (class in tf2rl.algos.vail)
VPG (class in tf2rl.algos.vpg)
W
WarpFrame (class in tf2rl.envs.atari_wrapper)
wrap_deepmind() (in module tf2rl.envs.atari_wrapper)
wrap_dqn() (in module tf2rl.envs.atari_wrapper)