Language

unilab.algos.torch.appo.runner.APPORunner¶

class unilab.algos.torch.appo.runner.APPORunner[source]¶

Bases: AsyncRunner

APPO async runner using shared memory.

Parameters:

env_name (str)
env_cfg_overrides (dict)
rl_cfg (dict)
device (str | None)
collector_device (str | None)
sim_backend (str)
num_envs (int)
steps_per_env (int)
num_workers (int)
replay_queue_size (int)
seed (int | None)
resume_path (str | None)

Methods

`__init__`(env_name, env_cfg_overrides, rl_cfg)
`close`()
`learn`([max_iterations, save_interval, ...])

__init__(env_name, env_cfg_overrides, rl_cfg, device=None, collector_device=None, sim_backend='mujoco', num_envs=1024, steps_per_env=24, num_workers=1, replay_queue_size=3, seed=None, resume_path=None)[source]¶

Parameters:

env_name (str)
env_cfg_overrides (dict)
rl_cfg (dict)
device (str | None)
collector_device (str | None)
sim_backend (str)
num_envs (int)
steps_per_env (int)
num_workers (int)
replay_queue_size (int)
seed (int | None)
resume_path (str | None)

learn(max_iterations=1500, save_interval=50, log_dir='logs', logger_type='tensorboard')[source]¶

Parameters:

max_iterations (int)
save_interval (int)
log_dir (str)
logger_type (str)

Return type:

None

close()¶

Return type:: None