Procedurally Generated Environment¶

class olympus.reinforcement.procgenenv.ProcEnvAdapter(proc_env, transforms=None)[source]¶

Bases: object

Methods

reset
step

reset(self)[source]¶

step(self, *args, **kwargs)[source]¶

class olympus.reinforcement.procgenenv.ProcgenEnvironment(env_name, transforms=None, rand_seed=None, train_size=1024, valid_size=128, test_size=128, parallel_env=8, num_thread=4, distribution_mode='easy')[source]¶

Bases: object

Attributes:	action_space `input_size` Return the size of the samples state_space `target_size` Return the size of the target test train valid

Methods

categories() Dataset tags so we can filter what we want depending on the task

close
load_state_dict
max
sample_action
state_dict

action_space¶

static categories()[source]¶: Dataset tags so we can filter what we want depending on the task

close(self)[source]¶

input_size¶: Return the size of the samples

load_state_dict(self, data)[source]¶

max(self)[source]¶

sample_action(self)[source]¶

state_dict(self)[source]¶

state_space¶

target_size¶: Return the size of the target

test¶

train¶

valid¶