#inductive-logic-programming

#inductive-logic-programming

In text-based reinforcement learning, agents perceive game states solely through natural language, challenging conventional methods of action representation and interaction.

To apply an ILP algorithm, first, EXPLORER needs to collect the State, Action, and Reward pairs while exploring the text-based environment. In a TBG, the two main components of the state are the state description and the inventory information of the agent.