()
| 50 | |
| 51 | |
| 52 | def test_temporal_difference_agent(): |
| 53 | seed = 12345 |
| 54 | max_steps = 200 |
| 55 | n_episodes = 5000 |
| 56 | |
| 57 | lr = 0.4 |
| 58 | n_tilings = 10 |
| 59 | epsilon = 0.10 |
| 60 | off_policy = True |
| 61 | grid_dims = [100, 100] |
| 62 | smooth_factor = 0.005 |
| 63 | temporal_discount = 0.999 |
| 64 | env = gym.make("LunarLander-v2") |
| 65 | obs_max = 1 |
| 66 | obs_min = -1 |
| 67 | |
| 68 | agent = TemporalDifferenceAgent( |
| 69 | env, |
| 70 | lr=lr, |
| 71 | obs_max=obs_max, |
| 72 | obs_min=obs_min, |
| 73 | epsilon=epsilon, |
| 74 | n_tilings=n_tilings, |
| 75 | grid_dims=grid_dims, |
| 76 | off_policy=off_policy, |
| 77 | temporal_discount=temporal_discount, |
| 78 | ) |
| 79 | |
| 80 | trainer = Trainer(agent, env) |
| 81 | trainer.train( |
| 82 | n_episodes, |
| 83 | max_steps, |
| 84 | seed=seed, |
| 85 | plot=True, |
| 86 | verbose=True, |
| 87 | render_every=None, |
| 88 | smooth_factor=smooth_factor, |
| 89 | ) |
| 90 | |
| 91 | |
| 92 | def test_dyna_agent(): |
nothing calls this directly
no test coverage detected