Open-Ended Learning Leads to Generally Capable Agents

Abstract

In this work we create agents that can perform well beyond a single, individual task, that exhibit much wider generalisation of behaviour to a massive, rich space of challenges. We define a universe of tasks within an environment domain and demonstrate the ability to train agents that are generally capable across this vast space and beyond. The environment is natively multi-agent, spanning the continuum of competitive, cooperative, and independent games, which are situated within procedurally generated physical 3D worlds. The resulting space is exceptionally diverse in terms of the challenges posed to agents, and as such, even measuring the learning progress of an agent is an open research problem. We propose an iterative notion of improvement between successive generations of agents, rather than seeking to maximise a singular objective, allowing us to quantify progress despite tasks being incomparable in terms of achievable rewards. We show that through constructing an open-ended learning process, which dynamically changes the training task distributions and training objectives such that the agent never stops learning, we achieve consistent learning of new behaviours. The resulting agent is able to score reward in every one of our humanly solvable evaluation levels, with behaviour generalising to many held-out points in the universe of tasks. Examples of this zero-shot generalisation include good performance on Hide and Seek, Capture the Flag, and Tag. Through analysis and hand-authored probe tasks we characterise the behaviour of our agent, and find interesting emergent heuristic behaviours such as trial-and-error experimentation, simple tool use, option switching, and cooperation. Finally, we demonstrate that the general capabilities of this agent could unlock larger scale transfer of behaviour through cheap finetuning.

References in corpus (6)

• Solving Rubik's Cube with a Robot Hand
• Reinforcement Learning with Unsupervised Auxiliary Tasks
• CPPN2GAN: Combining Compositional Pattern Producing Networks and GANs for Large-scale Pattern Generation
• Multi-task curriculum learning in a complex, visual, hard-exploration domain: Minecraft
• Language-Conditioned Goal Generation: a New Approach to Language Grounding for RL
• Contextual Games: Multi-Agent Learning with Side Information

Cited by in corpus (5)

• Transformers predicting the future. Applying attention in next-frame and time series forecasting
• Model based Multi-agent Reinforcement Learning with Tensor Decompositions
• Reinforcement Learning in Factored Action Spaces using Tensor Decompositions
• Eden: A Unified Environment Framework for Booming Reinforcement Learning Algorithms
• Neural Auto-Curricula