communication degree
Technology: Information Technology > Artificial Intelligence > Representation & Reasoning > Agents (1.00)
We thank the reviewers for their comments and will do our best to address them in our paper
Instead, they are automatically learned by the search algorithm (based on MCMC) in Section 3.4.
A Extending to Multi Round Communications
The formulation in Section 3 can be extended to multiple rounds of communications per time step. We synthesize these programs independently. There are four main hyper-parameters in our synthesis algorithm. We used cross validation to choose these parameters. Figure 7: Comparing program policy with RL policy that treats communications as actions.