A library of reinforcement learning components and agents
Highlights
EnvironmentLoop.run_episode()
for running a single episode.EnvironmentLoop.run()
to take num_steps
, allowing the control of step count rather than just episode count.make_dataset
.Minor changes and fixes
ConstantInfo
logger for logging constant information.should_update
parameter to the EnvironmentLoop
.make_reverb_dataset()
function.Minor version to fix a mismatch inversions between tf/tfp.
Other changes include: