def _compare_two_policies(policy1: NNPolicy, policy2: NNPolicy) -> None:
"""
Make sure two policies have the same output for the same input.
"""
decision_step, _ = mb.create_steps_from_brainparams(policy1.brain, num_agents=1)
run_out1 = policy1.evaluate(decision_step, list(decision_step.agent_id))
run_out2 = policy2.evaluate(decision_step, list(decision_step.agent_id))
np.testing.assert_array_equal(run_out2["log_probs"], run_out1["log_probs"])
def test_policy_evaluate(dummy_config, rnn, visual, discrete):
# Test evaluate
tf.reset_default_graph()
policy = create_policy_mock(dummy_config,
use_rnn=rnn,
use_discrete=discrete,
use_visual=visual)
decision_step, terminal_step = mb.create_steps_from_brainparams(
policy.brain, num_agents=NUM_AGENTS)
run_out = policy.evaluate(decision_step, list(decision_step.agent_id))
if discrete:
run_out["action"].shape == (NUM_AGENTS, len(DISCRETE_ACTION_SPACE))
else:
assert run_out["action"].shape == (NUM_AGENTS, VECTOR_ACTION_SPACE[0])