(
self,
trainer,
exploration_env,
evaluation_env,
exploration_data_collector: StepCollector,
evaluation_data_collector: PathCollector,
replay_buffer: ReplayBuffer,
batch_size,
max_path_length,
num_epochs,
num_eval_steps_per_epoch,
num_expl_steps_per_train_loop,
num_trains_per_train_loop,
num_train_loops_per_epoch=1,
min_num_steps_before_training=0,
)
source not stored for this graph (policy: none)
nothing calls this directly
no outgoing calls
no test coverage detected