Python Module Index

b | c | d | e | g | h | m | p | r | s | t | v | w


	b
	`bc_point`
	`bc_point_deterministic_policy`

	c
	`cem_cartpole`
	`cma_es_cartpole`

	d
	`ddpg_pendulum`
	`dqn_atari`
	`dqn_cartpole`
	`dqn_pong`

	e
	`erwr_cartpole`

	g
	`garage`
	`garage._dtypes`
	`garage._environment`
	`garage._functions`
	`garage.envs`
	`garage.envs.bullet`
	`garage.envs.bullet.bullet_env`
	`garage.envs.dm_control`
	`garage.envs.dm_control.dm_control_env`
	`garage.envs.dm_control.dm_control_viewer`
	`garage.envs.grid_world_env`
	`garage.envs.gym_env`
	`garage.envs.metaworld_set_task_env`
	`garage.envs.mujoco`
	`garage.envs.mujoco.half_cheetah_dir_env`
	`garage.envs.mujoco.half_cheetah_env_meta_base`
	`garage.envs.mujoco.half_cheetah_vel_env`
	`garage.envs.multi_env_wrapper`
	`garage.envs.normalized_env`
	`garage.envs.point_env`
	`garage.envs.task_name_wrapper`
	`garage.envs.task_onehot_wrapper`
	`garage.envs.wrappers`
	`garage.envs.wrappers.atari_env`
	`garage.envs.wrappers.clip_reward`
	`garage.envs.wrappers.episodic_life`
	`garage.envs.wrappers.fire_reset`
	`garage.envs.wrappers.grayscale`
	`garage.envs.wrappers.max_and_skip`
	`garage.envs.wrappers.noop`
	`garage.envs.wrappers.pixel_observation`
	`garage.envs.wrappers.resize`
	`garage.envs.wrappers.stack_frames`
	`garage.experiment`
	`garage.experiment.deterministic`
	`garage.experiment.experiment`
	`garage.experiment.meta_evaluator`
	`garage.experiment.snapshotter`
	`garage.experiment.task_sampler`
	`garage.np`
	`garage.np._functions`
	`garage.np.algos`
	`garage.np.algos.cem`
	`garage.np.algos.cma_es`
	`garage.np.algos.meta_rl_algorithm`
	`garage.np.algos.nop`
	`garage.np.algos.rl_algorithm`
	`garage.np.baselines`
	`garage.np.baselines.baseline`
	`garage.np.baselines.linear_feature_baseline`
	`garage.np.baselines.linear_multi_feature_baseline`
	`garage.np.baselines.zero_baseline`
	`garage.np.embeddings`
	`garage.np.embeddings.encoder`
	`garage.np.exploration_policies`
	`garage.np.exploration_policies.add_gaussian_noise`
	`garage.np.exploration_policies.add_ornstein_uhlenbeck_noise`
	`garage.np.exploration_policies.epsilon_greedy_policy`
	`garage.np.exploration_policies.exploration_policy`
	`garage.np.optimizers`
	`garage.np.optimizers.minibatch_dataset`
	`garage.np.policies`
	`garage.np.policies.fixed_policy`
	`garage.np.policies.policy`
	`garage.np.policies.scripted_policy`
	`garage.np.policies.uniform_random_policy`
	`garage.np.q_functions`
	`garage.np.q_functions.q_function`
	`garage.plotter`
	`garage.plotter.plotter`
	`garage.replay_buffer`
	`garage.replay_buffer.her_replay_buffer`
	`garage.replay_buffer.path_buffer`
	`garage.replay_buffer.replay_buffer`
	`garage.sampler`
	`garage.sampler._dtypes`
	`garage.sampler._functions`
	`garage.sampler.default_worker`
	`garage.sampler.env_update`
	`garage.sampler.fragment_worker`
	`garage.sampler.local_sampler`
	`garage.sampler.multiprocessing_sampler`
	`garage.sampler.ray_sampler`
	`garage.sampler.sampler`
	`garage.sampler.utils`
	`garage.sampler.vec_worker`
	`garage.sampler.worker`
	`garage.sampler.worker_factory`
	`garage.tf`
	`garage.tf._functions`
	`garage.tf.algos`
	`garage.tf.algos._rl2npo`
	`garage.tf.algos.ddpg`
	`garage.tf.algos.dqn`
	`garage.tf.algos.erwr`
	`garage.tf.algos.npo`
	`garage.tf.algos.ppo`
	`garage.tf.algos.reps`
	`garage.tf.algos.rl2`
	`garage.tf.algos.rl2ppo`
	`garage.tf.algos.rl2trpo`
	`garage.tf.algos.td3`
	`garage.tf.algos.te`
	`garage.tf.algos.te_npo`
	`garage.tf.algos.te_ppo`
	`garage.tf.algos.tnpg`
	`garage.tf.algos.trpo`
	`garage.tf.algos.vpg`
	`garage.tf.baselines`
	`garage.tf.baselines.continuous_mlp_baseline`
	`garage.tf.baselines.gaussian_cnn_baseline`
	`garage.tf.baselines.gaussian_cnn_baseline_model`
	`garage.tf.baselines.gaussian_mlp_baseline`
	`garage.tf.baselines.gaussian_mlp_baseline_model`
	`garage.tf.embeddings`
	`garage.tf.embeddings.encoder`
	`garage.tf.embeddings.gaussian_mlp_encoder`
	`garage.tf.models`
	`garage.tf.models.categorical_cnn_model`
	`garage.tf.models.categorical_gru_model`
	`garage.tf.models.categorical_lstm_model`
	`garage.tf.models.categorical_mlp_model`
	`garage.tf.models.cnn`
	`garage.tf.models.cnn_mlp_merge_model`
	`garage.tf.models.cnn_model`
	`garage.tf.models.cnn_model_max_pooling`
	`garage.tf.models.gaussian_cnn_model`
	`garage.tf.models.gaussian_gru_model`
	`garage.tf.models.gaussian_lstm_model`
	`garage.tf.models.gaussian_mlp_model`
	`garage.tf.models.gru`
	`garage.tf.models.gru_model`
	`garage.tf.models.lstm`
	`garage.tf.models.lstm_model`
	`garage.tf.models.mlp`
	`garage.tf.models.mlp_dueling_model`
	`garage.tf.models.mlp_merge_model`
	`garage.tf.models.mlp_model`
	`garage.tf.models.model`
	`garage.tf.models.module`
	`garage.tf.models.normalized_input_mlp_model`
	`garage.tf.models.parameter`
	`garage.tf.models.sequential`
	`garage.tf.optimizers`
	`garage.tf.optimizers._dtypes`
	`garage.tf.optimizers.conjugate_gradient_optimizer`
	`garage.tf.optimizers.first_order_optimizer`
	`garage.tf.optimizers.lbfgs_optimizer`
	`garage.tf.optimizers.penalty_lbfgs_optimizer`
	`garage.tf.plotter`
	`garage.tf.plotter.plotter`
	`garage.tf.policies`
	`garage.tf.policies.categorical_cnn_policy`
	`garage.tf.policies.categorical_gru_policy`
	`garage.tf.policies.categorical_lstm_policy`
	`garage.tf.policies.categorical_mlp_policy`
	`garage.tf.policies.continuous_mlp_policy`
	`garage.tf.policies.discrete_qf_argmax_policy`
	`garage.tf.policies.gaussian_gru_policy`
	`garage.tf.policies.gaussian_lstm_policy`
	`garage.tf.policies.gaussian_mlp_policy`
	`garage.tf.policies.gaussian_mlp_task_embedding_policy`
	`garage.tf.policies.policy`
	`garage.tf.policies.task_embedding_policy`
	`garage.tf.policies.uniform_control_policy`
	`garage.tf.q_functions`
	`garage.tf.q_functions.continuous_cnn_q_function`
	`garage.tf.q_functions.continuous_mlp_q_function`
	`garage.tf.q_functions.discrete_cnn_q_function`
	`garage.tf.q_functions.discrete_mlp_dueling_q_function`
	`garage.tf.q_functions.discrete_mlp_q_function`
	`garage.tf.samplers`
	`garage.tf.samplers.worker`
	`garage.torch`
	`garage.torch._functions`
	`garage.torch.algos`
	`garage.torch.algos.bc`
	`garage.torch.algos.ddpg`
	`garage.torch.algos.dqn`
	`garage.torch.algos.maml`
	`garage.torch.algos.maml_ppo`
	`garage.torch.algos.maml_trpo`
	`garage.torch.algos.maml_vpg`
	`garage.torch.algos.mtsac`
	`garage.torch.algos.pearl`
	`garage.torch.algos.ppo`
	`garage.torch.algos.sac`
	`garage.torch.algos.td3`
	`garage.torch.algos.trpo`
	`garage.torch.algos.vpg`
	`garage.torch.distributions`
	`garage.torch.distributions.tanh_normal`
	`garage.torch.embeddings`
	`garage.torch.embeddings.mlp_encoder`
	`garage.torch.modules`
	`garage.torch.modules.cnn_module`
	`garage.torch.modules.discrete_cnn_module`
	`garage.torch.modules.gaussian_mlp_module`
	`garage.torch.modules.mlp_module`
	`garage.torch.modules.multi_headed_mlp_module`
	`garage.torch.optimizers`
	`garage.torch.optimizers.conjugate_gradient_optimizer`
	`garage.torch.optimizers.differentiable_sgd`
	`garage.torch.optimizers.optimizer_wrapper`
	`garage.torch.policies`
	`garage.torch.policies.categorical_cnn_policy`
	`garage.torch.policies.context_conditioned_policy`
	`garage.torch.policies.deterministic_mlp_policy`
	`garage.torch.policies.discrete_cnn_policy`
	`garage.torch.policies.discrete_qf_argmax_policy`
	`garage.torch.policies.gaussian_mlp_policy`
	`garage.torch.policies.policy`
	`garage.torch.policies.stochastic_policy`
	`garage.torch.policies.tanh_gaussian_mlp_policy`
	`garage.torch.q_functions`
	`garage.torch.q_functions.continuous_mlp_q_function`
	`garage.torch.q_functions.discrete_cnn_q_function`
	`garage.torch.q_functions.discrete_dueling_cnn_q_function`
	`garage.torch.q_functions.discrete_mlp_q_function`
	`garage.torch.value_functions`
	`garage.torch.value_functions.gaussian_mlp_value_function`
	`garage.torch.value_functions.value_function`
	`garage.trainer`

	h
	`her_ddpg_fetchreach`

	m
	`maml_ppo_half_cheetah_dir`
	`maml_trpo_half_cheetah_dir`
	`maml_trpo_metaworld_ml10`
	`maml_trpo_metaworld_ml1_push`
	`maml_trpo_metaworld_ml45`
	`maml_vpg_half_cheetah_dir`
	`mtppo_metaworld_mt10`
	`mtppo_metaworld_mt1_push`
	`mtppo_metaworld_mt50`
	`mtsac_metaworld_mt10`
	`mtsac_metaworld_mt1_pick_place`
	`mtsac_metaworld_mt50`
	`mttrpo_metaworld_mt10`
	`mttrpo_metaworld_mt1_push`
	`mttrpo_metaworld_mt50`
	`multi_env_ppo`
	`multi_env_trpo`

	p
	`pearl_half_cheetah_vel`
	`pearl_metaworld_ml10`
	`pearl_metaworld_ml1_push`
	`pearl_metaworld_ml45`
	`ppo_memorize_digits`
	`ppo_pendulum`

	r
	`reps_gym_cartpole`
	`resume_training`
	`rl2_ppo_halfcheetah`
	`rl2_ppo_halfcheetah_meta_test`
	`rl2_ppo_metaworld_ml10`
	`rl2_ppo_metaworld_ml1_push`
	`rl2_ppo_metaworld_ml45`
	`rl2_trpo_halfcheetah`

	s
	`sac_half_cheetah_batch`
	`sim_policy`
	`step_bullet_kuka_env`
	`step_dm_control_env`
	`step_gym_env`

	t
	`td3_halfcheetah`
	`td3_pendulum`
	`te_ppo_metaworld_mt10`
	`te_ppo_metaworld_mt1_push`
	`te_ppo_metaworld_mt50`
	`te_ppo_point`
	`trpo_cartpole`
	`trpo_cartpole_bullet`
	`trpo_cartpole_recurrent`
	`trpo_cubecrash`
	`trpo_gym_tf_cartpole`
	`trpo_gym_tf_cartpole_pretrained`
	`trpo_pendulum`
	`trpo_pendulum_ray_sampler`
	`trpo_swimmer`
	`trpo_swimmer_ray_sampler`
	`tutorial_cem`
	`tutorial_vpg`

	v
	`vpg_cartpole`
	`vpg_pendulum`

	w
	`watch_atari`