Meta-learning in reinforcement learning

Neural Netw. 2003 Jan;16(1):5-9. doi: 10.1016/s0893-6080(02)00228-9.

Abstract

Meta-parameters in reinforcement learning should be tuned to the environmental dynamics and the animal performance. Here, we propose a biologically plausible meta-reinforcement learning algorithm for tuning these meta-parameters in a dynamic, adaptive manner. We tested our algorithm in both a simulation of a Markov decision task and in a non-linear control task. Our results show that the algorithm robustly finds appropriate meta-parameter values, and controls the meta-parameter time course, in both static and dynamic environments. We suggest that the phasic and tonic components of dopamine neuron firing can encode the signal required for meta-learning of reinforcement learning.

Publication types

  • Research Support, Non-U.S. Gov't

MeSH terms

  • Algorithms
  • Artificial Intelligence*
  • Decision Theory
  • Markov Chains
  • Reinforcement, Psychology*
  • Stochastic Processes