Awesome Open Source
Awesome Open Source


RL-botics is a toolbox with highly optimized implementations of Deep Reinforcement Learning algorithms for robotics developed with Keras and TensorFlow in Python3.

The objective was to have modular, clean and easy to read codebase so that the research community may build on top with ease. The implementations can be integrated with OpenAI Gym environments. The majority of the algorithms are Policy Search Methods as the toolbox is targetted for robotic applications.



Conda Environment

It is highly recommended to install this package in a virtual environment, such as Miniconda. Please find the Conda installation here.

To create a new conda environment called RL:

conda create -n RL python=3

To activate the environment:

source activate RL

To deactivate the environment:

source deactivate


To install the package, we recommend cloning the original package:

git clone
cd rl-botics
pip install -e .


To run any algorithm in the default setting, simply run:

cd rl_botics/<algo>/

For example, to run TRPO:

cd rl_botics/trpo/

Numerous other options can be added too, but it is recommended to modify the hyerperparameters in


The algorithms implemented are:

To be added:


All environments are in the envs directory. The environments available currently are:

  • Field Vision Rock Sampling (FVRS): A POMDP environment where the agent has to collect good rocks from partial observability.
  • Table Continuous: A POMDP environment emulation Human Robot Collaboration. The objective of the robot is to remove dirty dishes from the table without colliding with the human.

Toolbox Structure

All the algorithms are in the rl_botics directory. Each algorithm specified above has an individual directory.


The directory common contains common modular classes to easily build new algorithms.

  • approximators: Basic Deep Neural Networks (Dense, Conv, LSTM).
  • data_collection: Performs rollouts and collect observations and rewards
  • logger: Log training data and other information
  • plotter: Plot graphs
  • policies: Common policies such as Random, Softmax, Parametrized Softmax and Gaussian Policy
  • utils: Functions to compute the expected return, the Generalized Advantage Estimation (GAE), etc.

Algorithm Directories

Each algorithm directory contains at least 3 files:

  • Main script to run the algorithm
  • File to contain the default hyperparameters
  • <algo>.py: Implementation of the algorithm
  • (Optional) File containing some utility functions

Some algorithm directories may have additional files specific to the algorithm.


To contribute to this package, it is recommended to follow this structure:

  • The new algorithm directory should at least contain the 3 files mentioned above.
  • should contain at least the following functions:
    • main: Parses input argument, builds the environment and agent, and train the agent.
    • argparse: Parses input argument and loads default hyperparameters from
  • <algo>.py should contain at least the following methods:
    • __init__: Initializes the classes
    • _build_graph: Calls the following methods to build the TensorFlow graph:
      • _init_placeholders: Initialize TensorFlow placeholders
      • _build_policy: Build policy TensorFlow graph
      • _build_value_function: Build value function TensorFlow graph
      • _loss: Build policy loss function TensorFlwo graph
    • train: Main training loop called by
    • update_policy: Update the policy
    • update_value: Update the value function
    • print_results: Print the training results
    • process_paths: (optional) Process collected trajectories to return the feed dictionary for TensorFlow

It is recommended to check the structure of and follow a similar structure.


Suman Pal


MIT License.

Alternatives To Rl Botics
Select To Compare

Alternative Project Comparisons
Related Awesome Lists
Top Programming Languages
Top Projects

Get A Weekly Email With Trending Projects For These Topics
No Spam. Unsubscribe easily at any time.
Python (796,107
Algorithms (37,396
Machine Learning (36,527
Deep Learning (35,995
Tensorflow (22,284
Robot (17,242
Keras (10,424
Robotics (5,099
Reinforcement Learning (4,362
Rl (2,338
Machine Learning Algorithms (1,974
Openai (1,539
Deep Reinforcement Learning (1,007
Openai Gym (693
Ppo (606
Ddpg (540
Q Learning (395
Policy Gradient (293
Reinforcement Learning Algorithms (293
Trpo (129
Deep Q Learning (83