Open-ended search for environments and adapted agents using MAP-Elites

by   Emma Stensby Norstein, et al.

Creatures in the real world constantly encounter new and diverse challenges they have never seen before. They will often need to adapt to some of these tasks and solve them in order to survive. This almost endless world of novel challenges is not as common in virtual environments, where artificially evolving agents often have a limited set of tasks to solve. An exception to this is the field of open-endedness where the goal is to create unbounded exploration of interesting artefacts. We want to move one step closer to creating simulated environments similar to the diverse real world, where agents can both find solvable tasks, and adapt to them. Through the use of MAP-Elites we create a structured repertoire, a map, of terrains and virtual creatures that locomote through them. By using novelty as a dimension in the grid, the map can continuously develop to encourage exploration of new environments. The agents must adapt to the environments found, but can also search for environments within each cell of the grid to find the one that best fits their set of skills. Our approach combines the structure of MAP-Elites, which can allow the virtual creatures to use adjacent cells as stepping stones to solve increasingly difficult environments, with open-ended innovation. This leads to a search that is unbounded, but still has a clear structure. We find that while handcrafted bounded dimensions for the map lead to quicker exploration of a large set of environments, both the bounded and unbounded approach manage to solve a diverse set of terrains.


Self-Exploration in Complex Unknown Environments using Hybrid Map Representation

A hybrid map representation, which consists of a modified generalized Vo...

NovPhy: A Testbed for Physical Reasoning in Open-world Environments

Due to the emergence of AI systems that interact with the physical envir...

Enhanced POET: Open-Ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions

Creating open-ended algorithms, which generate their own never-ending st...

Neuro-Inspired Efficient Map Building via Fragmentation and Recall

Animals and robots navigate through environments by building and refinin...

Automatic Exploration of Textual Environments with Language-Conditioned Autotelic Agents

In this extended abstract we discuss the opportunities and challenges of...

Multi-Agent Autonomy: Advancements and Challenges in Subterranean Exploration

Artificial intelligence has undergone immense growth and maturation in r...

Using Unity to Help Solve Intelligence

In the pursuit of artificial general intelligence, our most significant ...

Please sign up or login with your details

Forgot password? Click here to reset