trajectory
In reinforcement learning, a sequence of tuples that represent a sequence of state transitions of the agent, where each tuple corresponds to the state, action, reward, and next state for a given state transition.
Plain English Explanation
In reinforcement learning, a sequence of tuples that represent a sequence of state transitions of the agent, where each tuple corresponds to the state, action, reward, and next state for a given state transition.
How is it used?
Practitioners refer to trajectory when building, training, or evaluating machine learning systems. It appears in research papers, product documentation, and technical discussions about AI capabilities and limitations.