schola.scripts.sb3.utils.RewardCallback
Class Definition
class schola.scripts.sb3.utils.RewardCallback(verbose=0, frequency=10, num_envs=1)Bases: CallbackList
Callback for logging rewards and steps taken by each environment in a multi-env setting.
Parameters
verbose
Type: int
Default: 0
Verbosity level.
frequency
Type: int
Default: 10
The frequency at which to log the rewards and steps taken.
num_envs
Type: int
Default: 1
The number of environments to log rewards and steps for.
Attributes
callbacks
Type: List[SingleEnvRewardCallback]
The list of RewardLoggingCallbacks for each environment.
curr_logging_interval
Type: int
The current logging interval.
logger
model
num_envs
Type: int
The number of environments to log rewards and steps for.
ready_to_log
Type: bool
Returns whether all environments are ready to log.
start_time
Type: int
The time at which the callback was created.
summarize_every
Type: int
The frequency at which to log the rewards and steps taken.
Methods
__init__
__init__(verbose=0, frequency=10, num_envs=1)init_callback
init_callback(model)Initialize the callback by saving references to the RL model and the training environment for convenience.
on_rollout_end
on_rollout_end()on_rollout_start
on_rollout_start()on_step
on_step()This method will be called by the model after each call to env.step().
on_training_end
on_training_end()on_training_start
on_training_start(locals_, globals_)update_child_locals
update_child_locals(locals_)Update the references to the local variables.
update_locals
update_locals(locals_)Update the references to the local variables.