Glossary term
Glossary term
Agentic Systems
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.
Created for this library
A logistics RL team logs full trajectories during simulation so the team can replay any episode for debugging.
A trading research team uses logged trajectories to train off-policy RL agents on historical market data.
A robotics RL team uses recorded trajectories from human demonstrations to bootstrap imitation learning before fine-tuning with RL.
Definition source: Google for Developers Machine Learning Glossary | Creative Commons Attribution 4.0 License