Articulated Animal AI: An Environment for Animal-like Cognition in a Limbed Agent
It provides a new testbench for evaluating animal cognition in AI agents, building incrementally on an existing framework.
The paper introduces the Articulated Animal AI Environment, an enhanced version of AnimalAI with agent limbs for more realistic animal-like movements and interactions, featuring integrated curriculum training and randomized tests to improve generalization.
This paper presents the Articulated Animal AI Environment for Animal Cognition, an enhanced version of the previous AnimalAI Environment. Key improvements include the addition of agent limbs, enabling more complex behaviors and interactions with the environment that closely resemble real animal movements. The testbench features an integrated curriculum training sequence and evaluation tools, eliminating the need for users to develop their own training programs. Additionally, the tests and training procedures are randomized, which will improve the agent's generalization capabilities. These advancements significantly expand upon the original AnimalAI framework and will be used to evaluate agents on various aspects of animal cognition.