This is a multi-agent reinforcement learning simulation I’ve been building as a personal project. It’s a grid-based combat environment with per-agent PPO training runtime. Some of the things I’ve been experimenting with: – Per-agent PPO (isolated optimizers p…
Large-scale multi-agent combat simulation with neural policy optimization.
Neural Siege is a high-performance, grid-based multi-agent simulation framework designed for research in emergent behaviors… [+11901 chars]
