Multi-Task Deep Reinforcement Learning with PopArt
| Autor: | Wojciech Marian Czarnecki, Matteo Hessel, Lasse Espeholt, Hubert Soyer, Hado van Hasselt, Simon Schmitt |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Computer science business.industry Process (engineering) Machine Learning (stat.ML) 020206 networking & telecommunications 02 engineering and technology General Medicine Machine Learning (cs.LG) Task (project management) Domain (software engineering) Statistics - Machine Learning Salient 0202 electrical engineering electronic engineering information engineering Reinforcement learning 020201 artificial intelligence & image processing Artificial intelligence State (computer science) Set (psychology) business |
| Zdroj: | AAAI |
| ISSN: | 2374-3468 2159-5399 |
| Popis: | The reinforcement learning (RL) community has made great strides in designing algorithms capable of exceeding human performance on specific tasks. These algorithms are mostly trained one task at the time, each new task requiring to train a brand new agent instance. This means the learning algorithm is general, but each solution is not; each agent can only solve the one task it was trained on. In this work, we study the problem of learning to master not one but multiple sequentialdecision tasks at once. A general issue in multi-task learning is that a balance must be found between the needs of multiple tasks competing for the limited resources of a single learning system. Many learning algorithms can get distracted by certain tasks in the set of tasks to solve. Such tasks appear more salient to the learning process, for instance because of the density or magnitude of the in-task rewards. This causes the algorithm to focus on those salient tasks at the expense of generality. We propose to automatically adapt the contribution of each task to the agent’s updates, so that all tasks have a similar impact on the learning dynamics. This resulted in state of the art performance on learning to play all games in a set of 57 diverse Atari games. Excitingly, our method learned a single trained policy - with a single set of weights - that exceeds median human performance. To our knowledge, this was the first time a single agent surpassed human-level performance on this multi-task domain. The same approach also demonstrated state of the art performance on a set of 30 tasks in the 3D reinforcement learning platform DeepMind Lab. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|