Bikramjit Banerjee

Sample Bounded Distributed Reinforcement Learning for Decentralized POMDPs

2021 · Proceedings of the AAAI Conference on Artificial Intelligence

Decentralized partially observable Markov decision processes (Dec-POMDPs) offer a powerful modeling technique for realistic multi-agent coordination problems under uncertainty. Prevalent solution techniques are centralized and assume prior knowledge of the model. We propose a distributed …

Latent Interactive A2C for Improved RL in Open Many-Agent Systems

2023 · arXiv (Cornell University)

There is a prevalence of multiagent reinforcement learning (MARL) methods that engage in centralized training. But, these methods involve obtaining various types of information from the other agents, which may not be feasible in competitive …