Contents Menu Expand Light mode Dark mode Auto light/dark mode
xpag 0.2.9 documentation
xpag 0.2.9 documentation
  • Installation
  • API reference
    • xpag.agents
      • xpag.agents.agent
        • xpag.agents.agent.Agent
      • xpag.agents.all_agents
        • xpag.agents.all_agents.agent_factory
        • xpag.agents.all_agents.SAC
      • xpag.agents.flax_agents
        • xpag.agents.flax_agents.sac
          • xpag.agents.flax_agents.sac.sac
            • xpag.agents.flax_agents.sac.sac.FlaxSAC
          • xpag.agents.flax_agents.sac.sac_from_jaxrl
            • xpag.agents.flax_agents.sac.sac_from_jaxrl.default_init
            • xpag.agents.flax_agents.sac.sac_from_jaxrl.sample_actions
            • xpag.agents.flax_agents.sac.sac_from_jaxrl.target_update
            • xpag.agents.flax_agents.sac.sac_from_jaxrl.update_actor
            • xpag.agents.flax_agents.sac.sac_from_jaxrl.update_critic
            • xpag.agents.flax_agents.sac.sac_from_jaxrl.update_temperature
            • xpag.agents.flax_agents.sac.sac_from_jaxrl.Batch
            • xpag.agents.flax_agents.sac.sac_from_jaxrl.Critic
            • xpag.agents.flax_agents.sac.sac_from_jaxrl.DoubleCritic
            • xpag.agents.flax_agents.sac.sac_from_jaxrl.MLP
            • xpag.agents.flax_agents.sac.sac_from_jaxrl.Model
            • xpag.agents.flax_agents.sac.sac_from_jaxrl.SACLearner
            • xpag.agents.flax_agents.sac.sac_from_jaxrl.Temperature
        • xpag.agents.flax_agents.sdqn
          • xpag.agents.flax_agents.sdqn.sdqn
            • xpag.agents.flax_agents.sdqn.sdqn.FeedForwardModel
            • xpag.agents.flax_agents.sdqn.sdqn.FlaxSDQN
            • xpag.agents.flax_agents.sdqn.sdqn.FlaxSDQNSetter
            • xpag.agents.flax_agents.sdqn.sdqn.TrainingState
        • xpag.agents.flax_agents.td3
          • xpag.agents.flax_agents.td3.td3
            • xpag.agents.flax_agents.td3.td3.FeedForwardModel
            • xpag.agents.flax_agents.td3.td3.FlaxTD3
            • xpag.agents.flax_agents.td3.td3.TrainingState
        • xpag.agents.flax_agents.tqc
          • xpag.agents.flax_agents.tqc.tqc
            • xpag.agents.flax_agents.tqc.tqc.huber
            • xpag.agents.flax_agents.tqc.tqc.quantile_loss
            • xpag.agents.flax_agents.tqc.tqc.update_actor
            • xpag.agents.flax_agents.tqc.tqc.update_critic
            • xpag.agents.flax_agents.tqc.tqc.FlaxTQC
            • xpag.agents.flax_agents.tqc.tqc.MultiQuantileCritic
            • xpag.agents.flax_agents.tqc.tqc.QuantileCritic
            • xpag.agents.flax_agents.tqc.tqc.TQCLearner
      • xpag.agents.rljax_agents
        • xpag.agents.rljax_agents.algorithm
          • xpag.agents.rljax_agents.algorithm.base_class
            • xpag.agents.rljax_agents.algorithm.base_class.actor_critic
              • xpag.agents.rljax_agents.algorithm.base_class.actor_critic.ActorCriticMixIn
              • xpag.agents.rljax_agents.algorithm.base_class.actor_critic.OffPolicyActorCritic
            • xpag.agents.rljax_agents.algorithm.base_class.base_algorithm
              • xpag.agents.rljax_agents.algorithm.base_class.base_algorithm.BaseAlgorithm
              • xpag.agents.rljax_agents.algorithm.base_class.base_algorithm.OffPolicyAlgorithm
          • xpag.agents.rljax_agents.algorithm.ddpg
            • xpag.agents.rljax_agents.algorithm.ddpg.DDPG
          • xpag.agents.rljax_agents.algorithm.misc
            • xpag.agents.rljax_agents.algorithm.misc.discor_mixin
              • xpag.agents.rljax_agents.algorithm.misc.discor_mixin.DisCorMixIn
          • xpag.agents.rljax_agents.algorithm.sac
            • xpag.agents.rljax_agents.algorithm.sac.SAC
          • xpag.agents.rljax_agents.algorithm.sac_discor
            • xpag.agents.rljax_agents.algorithm.sac_discor.SACDisCor
          • xpag.agents.rljax_agents.algorithm.td3
            • xpag.agents.rljax_agents.algorithm.td3.TD3
          • xpag.agents.rljax_agents.algorithm.tqc
            • xpag.agents.rljax_agents.algorithm.tqc.TQC
        • xpag.agents.rljax_agents.network
          • xpag.agents.rljax_agents.network.actor
            • xpag.agents.rljax_agents.network.actor.DeterministicPolicy
            • xpag.agents.rljax_agents.network.actor.StateDependentGaussianPolicy
            • xpag.agents.rljax_agents.network.actor.StateIndependentGaussianPolicy
          • xpag.agents.rljax_agents.network.base
            • xpag.agents.rljax_agents.network.base.MLP
          • xpag.agents.rljax_agents.network.critic
            • xpag.agents.rljax_agents.network.critic.ContinuousQFunction
            • xpag.agents.rljax_agents.network.critic.ContinuousQuantileFunction
            • xpag.agents.rljax_agents.network.critic.ContinuousVFunction
          • xpag.agents.rljax_agents.network.initializer
            • xpag.agents.rljax_agents.network.initializer.DeltaOrthogonal
        • xpag.agents.rljax_agents.rljax_interface
          • xpag.agents.rljax_agents.rljax_interface.DummyBuffer
          • xpag.agents.rljax_agents.rljax_interface.RljaxSAC
        • xpag.agents.rljax_agents.util
          • xpag.agents.rljax_agents.util.distribution
            • xpag.agents.rljax_agents.util.distribution.calculate_kl_divergence
            • xpag.agents.rljax_agents.util.distribution.evaluate_gaussian_and_tanh_log_prob
            • xpag.agents.rljax_agents.util.distribution.gaussian_and_tanh_log_prob
            • xpag.agents.rljax_agents.util.distribution.gaussian_log_prob
            • xpag.agents.rljax_agents.util.distribution.reparameterize_gaussian
            • xpag.agents.rljax_agents.util.distribution.reparameterize_gaussian_and_tanh
          • xpag.agents.rljax_agents.util.input
            • xpag.agents.rljax_agents.util.input.fake_action
            • xpag.agents.rljax_agents.util.input.fake_state
          • xpag.agents.rljax_agents.util.loss
            • xpag.agents.rljax_agents.util.loss.huber
            • xpag.agents.rljax_agents.util.loss.quantile_loss
          • xpag.agents.rljax_agents.util.optim
            • xpag.agents.rljax_agents.util.optim.clip_gradient
            • xpag.agents.rljax_agents.util.optim.clip_gradient_norm
            • xpag.agents.rljax_agents.util.optim.optimize
            • xpag.agents.rljax_agents.util.optim.soft_update
            • xpag.agents.rljax_agents.util.optim.weight_decay
          • xpag.agents.rljax_agents.util.preprocess
            • xpag.agents.rljax_agents.util.preprocess.add_noise
            • xpag.agents.rljax_agents.util.preprocess.get_q_at_action
            • xpag.agents.rljax_agents.util.preprocess.get_quantile_at_action
            • xpag.agents.rljax_agents.util.preprocess.preprocess_state
          • xpag.agents.rljax_agents.util.saving
            • xpag.agents.rljax_agents.util.saving.load_params
            • xpag.agents.rljax_agents.util.saving.save_params
    • xpag.buffers
      • xpag.buffers.buffer
        • xpag.buffers.buffer.Buffer
        • xpag.buffers.buffer.DefaultBuffer
        • xpag.buffers.buffer.DefaultEpisodicBuffer
        • xpag.buffers.buffer.EpisodicBuffer
      • xpag.buffers.jax_buffer
        • xpag.buffers.jax_buffer.JaxBuffer
        • xpag.buffers.jax_buffer.RBQueue
      • xpag.buffers.rljax_buffer
        • xpag.buffers.rljax_buffer.NStepBuffer
        • xpag.buffers.rljax_buffer.ReplayBuffer
        • xpag.buffers.rljax_buffer.RljaxBuffer
    • xpag.plotting
      • xpag.plotting.plotting
        • xpag.plotting.plotting.single_episode_plot
    • xpag.samplers
      • xpag.samplers.HER
      • xpag.samplers.jax_sampler
        • xpag.samplers.jax_sampler.JaxSampler
        • xpag.samplers.jax_sampler.RBUniformSampling
        • xpag.samplers.jax_sampler.ReplayBufferState
      • xpag.samplers.sampler
        • xpag.samplers.sampler.DefaultEpisodicSampler
        • xpag.samplers.sampler.DefaultSampler
        • xpag.samplers.sampler.Sampler
    • xpag.setters
      • xpag.setters.setter
        • xpag.setters.setter.CompositeSetter
        • xpag.setters.setter.DefaultSetter
        • xpag.setters.setter.Setter
    • xpag.tools
      • xpag.tools.eval
        • xpag.tools.eval.single_rollout_eval
        • xpag.tools.eval.SaveEpisode
      • xpag.tools.learn
      • xpag.tools.logging
        • xpag.tools.logging.eval_log
        • xpag.tools.logging.eval_log_reset
        • xpag.tools.logging.LevelFilter
      • xpag.tools.replay
        • xpag.tools.replay.brax_notebook_replay
        • xpag.tools.replay.mujoco_notebook_replay
      • xpag.tools.timing
      • xpag.tools.utils
        • xpag.tools.utils.datatype_convert
        • xpag.tools.utils.get_datatype
        • xpag.tools.utils.get_env_dimensions
        • xpag.tools.utils.hstack
        • xpag.tools.utils.logical_or
        • xpag.tools.utils.maximum
        • xpag.tools.utils.reshape
        • xpag.tools.utils.squeeze
        • xpag.tools.utils.tree_sum
        • xpag.tools.utils.where
        • xpag.tools.utils.DataType
    • xpag.wrappers
      • xpag.wrappers.brax_vec_env
      • xpag.wrappers.goalenv_wrapper
        • xpag.wrappers.goalenv_wrapper.CumulRewardWrapper
        • xpag.wrappers.goalenv_wrapper.GoalEnvWrapper
      • xpag.wrappers.gym_vec_env
      • xpag.wrappers.reset_done
        • xpag.wrappers.reset_done.ResetDoneWrapper
Back to top

xpag.agents.rljax_agents.util.input#

Functions

fake_action

fake_state

Next
xpag.agents.rljax_agents.util.input.fake_action
Previous
xpag.agents.rljax_agents.util.distribution.reparameterize_gaussian_and_tanh
Copyright © 2022-2023 CNRS
Made with Sphinx and @pradyunsg's Furo