AI-ON / Multitask-and-Transfer-Learning

Benchmark and build RL architectures that can do multitask and transfer learning.
143 stars 31 forks source link

Adversarial auxiliary signals #13

Open deontologician opened 6 years ago

deontologician commented 6 years ago

Create two separate networks that compete to explore the environment (together they form 1 agent) Idea is to have a reinforcement learning setup where:

The exploration network has no backprop into the weights of the prediction network, so it can't suggest degenerate representations (e.g. learning to output random noise to maximize surprise).

Influence is solely through the actions of the exploration network causing mispredictions. e.g. reality is always in between the exploration network and the prediction network

Considerations: