MathDB2 problems
- 0 votes0 replies0 views
Online mean-field sampling without a generative oracle
The setting is cooperative multi-agent reinforcement learning with a global decision-making agent and homogeneous local agents, where the current method uses a generative oracle to…
- 0 votes0 replies0 views
Conjecture on improved compressed environments for multi-agent reinforcement learning
Let MARL denote multi-agent reinforcement learning, and let compressed environments satisfy either of the constraints referenced in the source as or. Compressed-environment regret…