Imitation Learning in the Deep Learning Era: A Novel Taxonomy and Recent Advances

Imitation Learning - Learning paradigm in which an agent seeks to acquire a policy by observing and imitating the behavior of proficient agents, referred to as the expert

In Imitation Learning the expert provides Dataset D of expert-related behavioral data

In english: The format of the input the agent can learn from

• M is a positive number
• In the state the expert took action
• In the state the expert took action and the resulting state was
• pre-action state and post-action state

In english: For a specific state the probability distribution of all the possible actions

• S = the state space (set of all possible states)
• A = the action space (set of all possible actions)
• = the set of probability distributions over actions in A

Explicit Imitation - The Dataset provided only contains state-action pairs

Implicit Imitation - The Dataset ONLY contains state transitions