Generalizing Emergent Communication
arXiv:2001.01772
Abstract
We converted the recently developed BabyAI grid world platform to a sender/receiver setup in order to test the hypothesis that established deep reinforcement learning techniques are sufficient to incentivize the emergence of a grounded discrete communication protocol between generalized agents. This is in contrast to previous experiments that employed straight-through estimation or specialized inductive biases. Our results show that these can indeed be avoided, by instead providing proper environmental incentives. Moreover, they show that a longer interval between communications incentivized more abstract semantics. In some cases, the communicating agents adapted to new environments more quickly than a monolithic agent, showcasing the potential of emergent communication for transfer learning and generalization in general.
arXiv commentSummary of a master thesis by Thomas A. Unger, supervised by Elia Bruni at the University of Amsterdam from January to August 2019. 9 pages, 6 figures, 2 tables
References in corpus (9)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Categorical Reparameterization with Gumbel-Softmax
- Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
- Learning to Communicate with Deep Multi-Agent Reinforcement Learning
- The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
- Emergence of Grounded Compositional Language in Multi-Agent Populations
- Scalable agent alignment via reward modeling: a research direction
- Compositional Obverter Communication Learning From Raw Visual Input
- Evolving Culture vs Local Minima