TianShou
0.1

Tutorials:

  • DDPG (Deep Deterministic Policy Gradient) with TianShou
    • Make an Environment
    • Build the Networks
    • Construct Optimization Methods
    • Specify Data Acquisition
    • Start Training!

API Docs

  • tianshou.core.policy
    • Base class
    • Deterministic policy
    • Distributional policy
    • DQN policy
  • tianshou.core.value_function
    • Base class
    • State value
    • Action value
  • tianshou.core.losses
  • tianshou.core.opt
  • tianshou.core.random
  • tianshou.core.utils
  • tianshou.data.data_buffer
    • Base class
    • Batch set
    • Replay buffer base
    • Vanilla replay buffer
  • tianshou.data.advantage_estimation
  • tianshou.data.data_collector
  • tianshou.data.tester
TianShou
  • Docs »
  • Overview: module code

All modules for which code is available

  • tianshou.core.losses
  • tianshou.core.opt
  • tianshou.core.policy.base
  • tianshou.core.policy.deterministic
  • tianshou.core.policy.distributional
  • tianshou.core.policy.dqn
  • tianshou.core.random
  • tianshou.core.utils
  • tianshou.core.value_function.action_value
  • tianshou.core.value_function.base
  • tianshou.core.value_function.state_value
  • tianshou.data.advantage_estimation
  • tianshou.data.data_buffer.base
  • tianshou.data.data_buffer.batch_set
  • tianshou.data.data_buffer.replay_buffer_base
  • tianshou.data.data_buffer.vanilla
  • tianshou.data.data_collector
  • tianshou.data.tester

© Copyright 2018, TSAIL.

Built with Sphinx using a theme provided by Read the Docs.