Scaling All-Goals Updates in Reinforcement Learning Using Convolutional Neural Networks

Understand

Being able to reach any desired location in the environment can be a valuable asset for an agent.

• Learning a policy to navigate between all pairs of states individually is often not feasible.
• An all-goals updating algorithm uses each transition to learn Q-values towards all goals simultaneously and off-policy.
• However the expensive numerous updates in parallel limited the approach to small tabular cases so far.