Software

Open-source software from our lab. Most of it is based on personal software contributions from our lab members.
Disclaimer: It is research-level source code, so there is no support provided.

Tonic logo with padding areas

Tonic: A Deep Reinforcement Learning Library for Fast Prototyping and Benchmarking

  • a collection of configurable modules such as: exploration strategies, memories, neural networks, and optimizers
  • a collection of baseline agents built with these modules
  • support for the two most popular deep learning frameworks: TensorFlow and PyTorch
  • support for the three most popular sets of continuous control environments: OpenAI Gym, DeepMind Control Suite and PyBullet
  • a large-scale benchmark of the baseline agents on 70 tasks
  • scripts to train in a reproducible way, plot results, and play with trained agents
Repository: https://github.com/fabiopardo/tonic
Data: https://github.com/fabiopardo/tonic_data

Q-map: Goal-Oriented Reinforcement Learning Software

Q-map uses a convolutional autoencoder-like architecture combined with Q-learning to efficiently learn to reach all possible on-screen coordinates in complex games such as Mario Bros or Montezuma's Revenge. The agent discovers correlations between visual patterns and navigation and is able to explore quickly by performing mutliple steps in the direction of random goals.

Paper: https://arxiv.org/abs/1810.02927
Source code: https://github.com/fabiopardo/qmap
Videos: https://sites.google.com/view/q-map-rl
Robot DE NIRO close-up

Robot DE NIRO – Autonomous Capabilities Software

This release contains implementation of DE NIRO’s state-of-the-art capabilities, including autonomous navigation, localization and mapping, manipulation, face-, speech- and object recognition, speech I/O, a state machine and a GUI. The software is integrated with ROS and written in Python. Online documentation is available.

Source code: https://github.com/FabianFalck/deniro 
Docs: https://robot-intelligence-lab.gitlab.io/fezzik-docs/
Video: https://www.youtube.com/watch?v=qnvPpNyWY2M
Branching Dueling Q-Network (BDQ)

Branching Dueling Q-Network (BDQ)

Action-branching agents provides a set of deep reinforcement learning agents based on the incorporation of the action-branching architecture into the existing reinforcement learning algorithms. This software release contains the implementation of Branching Dueling Q-Network (BDQ), a novel agent that is based on the incorporation of our action branching architecture into the Deep Q-Network (DQN) algorithm. The software also contains several extensions of BDQ, such as Double Q-Learning, Dueling Network Architectures, and Prioritized Experience Replay.

>>> Download from here <<<

Datasets

Datasets with recordings from the sensors of our robots during our research experiments. It can enable other researchers who do not have access to such robots to conduct research on perception, recognition, machine learning, etc.

Robot DE NIRO at the Imperial Festival

Robot DE NIRO - Multi-sensor Dataset

This dataset contains a number of recordings from the sensors of Robot DE NIRO. The sensors include 2D and 3D laser scanners (LIDAR), cameras, RGB-D sensors (Kinect), ultrasonic and infrared proximity sensors, 360-degree panoramic camera rig, stereo vision, etc. The dataset is stored in ROS bag format and is rather large (a few GBs).

>>> Download coming soon... <<<