minqi/learning-to-communicate-pytorch

This is a PyTorch implementation of the original Lua code release. This codebase implements two approaches to learning discrete communication protocols for playing collaborative games: Reinforced Inter-Agent Learning (RIAL), in which agents learn a factorized deep Q-learning policy across game actions and messages, and Differentiable Inter-Agent Learning (DIAL), in which the message vectors are directly learned by backpropagating errors through a noisy communication channel during training, and discretized to binary vectors during test time. While RIAL and DIAL share the same individual network architecture, one would expect learning to be more efficient under DIAL, which directly backpropagates downstream errors during training, a fact that is verified in comparing the performance of the two approaches. This chart was generated by plotting an exponentially-weighted average across 20 trials for each curve. JSON configuration files passed to main.py should consist of the following key-value pairs: You can use analyze_results.py to graph results output by main.py.