Terminology Edit

  • Deterministic vs. randomized policy

Training Edit

  • Optimal Learning Trajectories: Some algorithms assume that the Optimal Learning Trajectories (OLTs) are known for all learning examples. An OLT is a sequence of actions that, given an input, leads from the initial state to the correct output.
  • Optimal Learning Policy: Some algorithms assume that for each learning example, we know an Optimal Learning Policy (OLP). The OLP is a procedure that knows the best decision to perform for any state of the prediction space.

Arguments for reinforcement learning Edit

There's not enough training data for supervised learning to succeed in many tasks. See also Yoshua Bengio's argument for unsupervised learning[note 1].

Anthropomorphic argument (albeit a weak one): children learn from a small amount of "labeled" data. Humans of all age learn by trial-and-error, environment simulation,...

Implementation Edit

See also Edit

References Edit

Notes Edit

  1. Note that he means non-standard unsupervised learning in which an agent can also interact with its environment.