Multi-agent hierarchical reinforcement learning with dynamic termination

In a multi-agent system, an agent's optimal policy will typically depend on the policies of other agents. Predicting the behaviours of others, and responding promptly to changes in such behaviours, is therefore a key issue in multi-agent systems research. One obvious possibility is for each agent to broadcast their current intention, for example, the currently executed option in a hierarchical RL framework. However, this approach results in inflexible agents when options have an extended duration. While adjusting the executed option at each step improves flexibility from a single-agent perspective, frequent changes in options can induce inconsistency between an agent's actual behaviour and its broadcasted intention. In order to balance flexibility and predictability, we propose a dynamic termination Bellman equation that allows the agents to flexibly terminate their options.