Logo
latest

Introduction

  • Introduction
  • Installation
  • Algorithms
  • Running Experiments
  • Experiment Outputs
  • Plotting Results

Introduction to RL

  • Part 1: Key Concepts in RL
  • Part 2: Kinds of RL Algorithms
  • Part 3: Intro to Policy Optimization

Resources

  • Spinning Up as a Deep RL Researcher
  • Key Papers in Deep RL
  • Exercises
  • Benchmarks for Spinning Up Implementations

Algorithms Docs

  • Vanilla Policy Gradient
  • Trust Region Policy Optimization
  • Proximal Policy Optimization
  • Deep Deterministic Policy Gradient
  • Twin Delayed DDPG
  • Soft Actor-Critic

Utilities Docs

  • Logger
  • Plotter
  • MPI Tools
  • Run Utils
gym_pybullet_mobilerobot
  • Docs »
  • Index
  • Edit on GitHub

Index

Symbols | C | L

Symbols

  • --act, --ac_kwargs:activation
    • command line option
  • --count
    • command line option
  • --cpu, --num_cpu
    • command line option
  • --data_dir
    • command line option
  • --datestamp
    • command line option
  • --env, --env_name
    • command line option
  • --exclude=[EXC ...]
    • command line option
  • --exp_name
    • command line option
  • --hid, --ac_kwargs:hidden_sizes
    • command line option
  • --select=[SEL ...]
    • command line option
  • -d, --deterministic
    • command line option
  • -i I, --itr=I, default=-1
    • command line option
  • -l L, --len=L, default=0
    • command line option
  • -l, --legend=[LEGEND ...]
    • command line option
  • -n N, --episodes=N, default=100
    • command line option
  • -nr, --norender
    • command line option
  • -s, --smooth=S, default=1
    • command line option
  • -x, --xaxis=XAXIS, default='TotalEnvInteracts'
    • command line option
  • -y, --value=[VALUE ...], default='Performance'
    • command line option

C

  • command line option
    • --act, --ac_kwargs:activation
    • --count
    • --cpu, --num_cpu
    • --data_dir
    • --datestamp
    • --env, --env_name
    • --exclude=[EXC ...]
    • --exp_name
    • --hid, --ac_kwargs:hidden_sizes
    • --select=[SEL ...]
    • -d, --deterministic
    • -i I, --itr=I, default=-1
    • -l L, --len=L, default=0
    • -l, --legend=[LEGEND ...]
    • -n N, --episodes=N, default=100
    • -nr, --norender
    • -s, --smooth=S, default=1
    • -x, --xaxis=XAXIS, default='TotalEnvInteracts'
    • -y, --value=[VALUE ...], default='Performance'
    • logdir

L

  • logdir
    • command line option

© Copyright 2019, Sarathmenon Revision 47fb4935.

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