|View source on GitHub|
Trajectory given transitions.
tf_agents.trajectories.trajectory.from_transition( time_step, action_step, next_time_step )
Used in the notebooks
|Used in the tutorials|
from_transition is used by a driver to convert sequence of transitions into
Trajectory for efficient storage. Then an agent (e.g.
ppo_agent.PPOAgent) converts it back to transitions by invoking
Note that this method does not add a time dimension to the Tensors in the
Trajectory. This means that if your transitions don't already
include a time dimension, the
Trajectory cannot be passed to