Closed peakfly closed 1 year ago
Oh,"g_policy"and"g_policy_3d" are not defined in the main.py. Is this a bug?
# Save best models
if (step * num_scenes) % args.save_interval < \
num_scenes:
if len(g_episode_rewards) >= 1000 and \
(np.mean(g_episode_rewards) >= best_g_reward) \
and not args.eval:
torch.save(g_policy.state_dict(),
os.path.join(log_dir, "model_best_explore.pth"))
torch.save(g_policy_3d.state_dict(),
os.path.join(log_dir, "model_best_identify.pth"))
best_g_reward = np.mean(g_episode_rewards)
❓ Questions and Help When I trained on the 2xRTX3090,the error occurred after 01d 02h 15m 29s. Is there a problem with my Settings? The file sh_train_mp3d.sh is as follows.
The Error occurs