Agents
PettingZoo: A Standard API for Multi-Agent Reinforcement Learning J. K. Terry
This paper introduces the PettingZoo library and the accompanying Agent Environment Cycle ("AEC") games model. PettingZoo is a library of diverse sets of multi-agent environments with a universal, elegant Python API. PettingZoo was developed with the goal of accelerating research in Multi-Agent Reinforcement Learning ("MARL "), by making work more interchangeable, accessible and reproducible akin to what OpenAI's Gym library did for single-agent reinforcement
Sequential Information Design: Learning to Persuade in the Dark
We consider settings where the receiver faces a sequential decision making (SDM) problem.
Multi-agent active perception with prediction rewards (Supplementary material)
This supplementary document is structured as follows.
Multi-agent active perception with prediction rewards
Multi-agent active perception is a task where a team of agents cooperatively gathers observations to compute a joint estimate of a hidden variable.
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.
