Projects

Symbolic Behaviour Benchmark (S2B)

Suite of OpenAI Gym-compatible multi-agent reinforcement learning environment to benchmark for behavioral traits pertaining to symbolic behaviours (primarily: being receptive, constructive, malleable, and separable) using referential games.

ReferentialGym

Out-of-the-box Referential Games for Languages Emergence and Grounding in visual modality.

GazeboDomainRandomization

This is an implementation of some Domain Randomization tools within the ROS+Gazebo framework, following the work of Tobin et al.'s 'Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worl'.

RelationalReasoning

State-of-the-art relational reasoning algorithms, using PyTorch.