• Search by Module
• Search by Words
• Search Projects

• Java
• Python
• JavaScript
• TypeScript
• C++
• Scala
• Blog

• RL_toolbox-master
  • parameters.py
  • build
    • lib.linux-x86_64-2.7
      • RLTracking
        • parameters.py
        • test_plot.py
        • trpo_tracking.py
        • __init__.py
        • trpo_continous.py
        • environment.py
      • RLToolbox
        • network
          • __init__.py
          • network.py
        • storage
          • storage_continous.py
          • storage_image.py
          • storage_continous_parallel_image.py
          • storage_replay.py
          • __init__.py
          • storage_continous_parallel.py
        • parameters.py
        • agent
          • TRPO_agent.py
          • DQN_agent.py
          • __init__.py
          • TRPO_parallel_agent.py
        • environment
          • __init__.py
          • gym_environment.py
        • toolbox
          • sample
            • e_greedy.py
            • __init__.py
          • common
            • __init__.py
            • utils.py
          • distribution
            • diagonal_category.py
            • diagonal_gaussian.py
            • __init__.py
          • baseline
            • baseline_zeros.py
            • baseline_lstsq.py
            • baseline_tensorflow.py
            • baseline_average_reward.py
            • __init__.py
            • baseline_tf_image.py
          • __init__.py
          • math
            • __init__.py
            • krylov.py
          • logger
            • logger.py
            • __init__.py
        • __init__.py
        • experiment
          • trpo_parallel.py
          • __init__.py
          • trpo_continous.py
          • dqn_mountaincar.py
        • algorithm
          • TRPO.py
          • __init__.py
  • RLToolbox.egg-info
    • top_level.txt
    • dependency_links.txt
    • PKG-INFO
    • SOURCES.txt
  • a3c
    • parameters.py
    • a3c_continous.py
    • rmsprops_applier.py
    • __init__.py
  • RLToolbox
    • network
      • Vgg16Net.py
      • alexNet
        • bvlc_alexnet.py
        • __init__.py
      • kaffe
        • graph.py
        • transformers.py
        • layers.py
        • __init__.py
        • errors.py
        • tensorflow
          • transformer.py
          • __init__.py
          • network.py
        • shapes.py
        • caffe
          • __init__.py
          • resolver.py
      • __init__.py
      • network.py
      • Cifar10.py
      • AlexNet.py
    • storage
      • storage_continous.py
      • storage_replay.pyc
      • storage_image.py
      • storage_continous_parallel_image.py
      • __init__.pyc
      • storage_replay.py
      • storage_continous_parallel.pyc
      • storage_continous.pyc
      • __init__.py
      • storage_continous_parallel.py
    • parameters.py
    • RLToolbox.egg-info
      • top_level.txt
      • dependency_links.txt
      • PKG-INFO
      • SOURCES.txt
    • LICENSE
    • agent
      • AC_agent.py
      • A3C_agent.py
      • TRPO_agent.py
      • DQN_agent.py
      • __init__.py
      • TRPO_parallel_agent.py
    • environment
      • __init__.pyc
      • __init__.py
      • gym_environment.py
      • gym_environment.pyc
    • toolbox
      • sample
        • e_greedy.py
        • __init__.pyc
        • __init__.py
        • e_greedy.pyc
      • common
        • __init__.pyc
        • __init__.py
        • utils.py
        • utils.pyc
      • __init__.pyc
      • distribution
        • diagonal_category.py
        • diagonal_gaussian.py
        • __init__.pyc
        • __init__.py
        • diagonal_gaussian.pyc
      • baseline
        • baseline_zeros.py
        • baseline_lstsq.py
        • __init__.pyc
        • baseline_zeros.pyc
        • baseline_tensorflow.py
        • baseline_average_reward.py
        • __init__.py
        • baseline_lstsq.pyc
        • baseline_tf_image.py
      • __init__.py
      • math
        • statistics.py
        • __init__.pyc
        • krylov.pyc
        • __init__.py
        • krylov.py
      • logger
        • logger.pyc
        • __init__.pyc
        • logger.py
        • __init__.py
    • __init__.py
    • README.md
    • experiment
      • trpo_ac_pendulen.py
      • trpo_parallel.py
      • __init__.py
      • trpo_continous.py
      • dqn_mountaincar.py
    • .gitignore
    • algorithm
      • TRPO.pyc
      • __init__.pyc
      • TRPO.py
      • ActorCritic.py
      • __init__.py
  • dist
    • RLToolbox-2.0.3.tar.gz
    • RLToolbox-2.0.7.tar.gz
    • RLToolbox-2.0.6.tar.gz
    • RLToolbox-2.0.4.tar.gz
    • RLToolbox-2.0.2.tar.gz
    • RLToolbox-1.0.1.tar.gz
    • RLToolbox-2.0.6-py2.7.egg
    • RLToolbox-2.0.5-py2.7.egg
    • RLToolbox-2.0.1.tar.gz
    • RLToolbox-2.0.5.tar.gz
  • MANIFEST
  • LICENSE
  • log
    • 2017-01-08-20:39:49.csv
    • 2017-01-08-20:52:50.csv
    • 2017-01-08-20:55:27.csv
  • nohup.out
  • setup.py
  • README.md
  • requirements.txt
  • experiment
    • parameters.pyc
    • trpo_parallel.py
    • parameters.py
    • MUJOCO_LOG.TXT
    • dqn_CartPole-v0.py
    • trpo_continous.py
    • dqn_mountaincar.py
  • .idea
    • RL_toolbox.iml
  • .gitignore

RL_toolbox

all the algorithm is running on pycharm IDE, or the package loss error may exist.

implemented algorithm: trpo a3c

• a3c:for continous action space, use multi processes, but saving model has not been implemented.
• trpo:for continous and discrete action space

run

• a3c:run a3c/a3c_continous.py in pycharm IDE
• trpo:run experiment/trpo_continous.py in pycharm IDE

contain some useful reinforcement learning algorithm and relative tool