108 lines
3.9 KiB
Python
108 lines
3.9 KiB
Python
"""The shared curriculum needs mature evidence on both commanded axes."""
|
|
|
|
from types import SimpleNamespace
|
|
|
|
import pytest
|
|
|
|
torch = pytest.importorskip("torch")
|
|
|
|
from mjrl.tasks.curriculum import CommandRangeCurriculum
|
|
|
|
|
|
PARAMS = {
|
|
"fractions": (0.4, 0.7, 1.0),
|
|
"ceilings": (1.0, 0.0, 0.5),
|
|
"command_name": "twist",
|
|
"dwell_steps": 150,
|
|
"min_steps": 10,
|
|
"min_samples": 3,
|
|
"gate_ratio": 0.4,
|
|
"ema_alpha": 1.0,
|
|
}
|
|
|
|
|
|
def _inputs(monkeypatch):
|
|
monkeypatch.delenv("MJRL_COMMAND_LEVEL", raising=False)
|
|
ranges = SimpleNamespace()
|
|
term = SimpleNamespace(
|
|
cfg=SimpleNamespace(ranges=ranges, resampling_time_range=(3.0, 7.0)),
|
|
metrics={"error_vel_xy": torch.zeros(3), "error_vel_yaw": torch.zeros(3)},
|
|
)
|
|
env = SimpleNamespace(
|
|
command_manager=SimpleNamespace(get_term=lambda _: term),
|
|
common_step_counter=0,
|
|
max_episode_length=120,
|
|
episode_length_buf=torch.tensor([70, 70, 70]),
|
|
step_dt=0.1,
|
|
)
|
|
ladder = CommandRangeCurriculum(SimpleNamespace(params=PARAMS), env)
|
|
return env, term, ladder
|
|
|
|
|
|
def test_curriculum_waits_for_real_rollouts_and_pools_staggered_resets(monkeypatch) -> None:
|
|
env, term, ladder = _inputs(monkeypatch)
|
|
report = ladder(env, torch.arange(3), **PARAMS)
|
|
assert report["level"] == 0
|
|
assert term.cfg.ranges.lin_vel_x == pytest.approx((-0.4, 0.4))
|
|
assert ladder.err_ema is None
|
|
|
|
env.common_step_counter = 119
|
|
ladder(env, torch.arange(3), **PARAMS)
|
|
assert ladder.err_ema is None, "initial randomized episode ages must not count"
|
|
|
|
env.common_step_counter = 151
|
|
for index in (0, 1):
|
|
report = ladder(env, torch.tensor([index]), **PARAMS)
|
|
assert report["level"] == 0
|
|
assert ladder.err_ema is None
|
|
report = ladder(env, torch.tensor([2]), **PARAMS)
|
|
assert report["level"] == 1
|
|
assert term.cfg.ranges.lin_vel_x == pytest.approx((-0.7, 0.7))
|
|
assert term.cfg.ranges.lin_vel_y == (0.0, 0.0)
|
|
assert term.cfg.ranges.ang_vel_z == pytest.approx((-0.35, 0.35))
|
|
assert ladder.err_ema is None, "promotion must discard evidence from the previous stage"
|
|
|
|
|
|
@pytest.mark.parametrize("blocked", ["error_vel_xy", "error_vel_yaw"])
|
|
def test_bad_tracking_on_either_axis_blocks_promotion(monkeypatch, blocked) -> None:
|
|
env, term, ladder = _inputs(monkeypatch)
|
|
env.common_step_counter = 200
|
|
term.metrics[blocked].fill_(0.3)
|
|
assert ladder(env, torch.arange(3), **PARAMS)["level"] == 0
|
|
|
|
term.metrics[blocked].zero_()
|
|
assert ladder(env, torch.arange(3), **PARAMS)["level"] == 1
|
|
|
|
|
|
@pytest.mark.parametrize("saved", [None, {"level": 0, "last_promotion_step": 1}])
|
|
def test_resume_ignores_randomized_episode_ages_until_a_fresh_horizon(monkeypatch, saved) -> None:
|
|
env, term, ladder = _inputs(monkeypatch)
|
|
start = 10_000
|
|
ladder.load_state_dict(saved, step=start)
|
|
assert "_evidence_start_step" not in ladder.state_dict()
|
|
for offset in (0, 1, env.max_episode_length - 1):
|
|
env.common_step_counter = start + offset
|
|
assert ladder(env, torch.arange(3), **PARAMS)["level"] == 0
|
|
assert ladder.err_ema is None
|
|
assert term.cfg.ranges.lin_vel_x == pytest.approx((-0.4, 0.4))
|
|
|
|
env.common_step_counter += 1
|
|
assert ladder(env, torch.arange(3), **PARAMS)["level"] == 1
|
|
|
|
|
|
def test_loading_again_restarts_the_horizon_and_drops_partial_samples(monkeypatch) -> None:
|
|
env, _, ladder = _inputs(monkeypatch)
|
|
start = 10_000
|
|
saved = ladder.state_dict()
|
|
ladder.load_state_dict(saved, step=start)
|
|
env.common_step_counter = start + env.max_episode_length
|
|
assert ladder(env, torch.tensor([0, 1]), **PARAMS)["level"] == 0
|
|
|
|
start = 20_000
|
|
ladder.load_state_dict(saved, step=start)
|
|
env.common_step_counter = start + env.max_episode_length - 1
|
|
assert ladder(env, torch.arange(3), **PARAMS)["level"] == 0
|
|
env.common_step_counter += 1
|
|
assert ladder(env, torch.tensor([2]), **PARAMS)["level"] == 0
|
|
assert ladder(env, torch.tensor([0, 1]), **PARAMS)["level"] == 1
|