(checkpoint, deterministic=False)
| 7 | |
| 8 | |
| 9 | def experiment(checkpoint, deterministic=False): |
| 10 | d = joblib.load(checkpoint) |
| 11 | print("Epoch = %d" % d["epoch"]) |
| 12 | |
| 13 | print(d) |
| 14 | |
| 15 | algorithm = d["algorithm"] |
| 16 | algorithm.render = True |
| 17 | print(algorithm.discriminator) |
| 18 | |
| 19 | if deterministic: |
| 20 | algorithm.exploration_policy = MakeDeterministic(algorithm.exploration_policy) |
| 21 | |
| 22 | # print(algorithm.grad_pen_weight) |
| 23 | |
| 24 | # algorithm.do_not_train = True |
| 25 | # algorithm.do_not_eval = True |
| 26 | # for i in range(100): |
| 27 | # algorithm.generate_exploration_rollout() |
| 28 | |
| 29 | algorithm.num_steps_between_updates = 1000000 |
| 30 | algorithm.train_online() |
| 31 | |
| 32 | return 1 |
| 33 | |
| 34 | |
| 35 | if __name__ == "__main__": |
no test coverage detected