search

openai / baselines

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms
MIT License
15.63k stars 4.86k forks source link

The Atari pretrained model downloader be removed? #302

Open louchenyao opened 6 years ago

louchenyao commented 6 years ago

In DQN's README, it gives a way to download the pretrained model:

python -m baselines.deepq.experiments.atari.download_model

But it seems the atari.download_model already be removed in experiments directory.

unixpickle commented 6 years ago

I think this was removed because it was out of date and stopped working. You can browse a different commit to find the script and try it.

Ideally, this should be removed from the README if it indeed no longer works. Otherwise, it should be added back to the repo.

yrevar commented 6 years ago

Is there any alternative? I'm looking for pre-trained model of Pong and few other Atari games for benchmarking and experiments.

DanielTakeshi commented 6 years ago

@yrevar i strongly recommend training them again if you can. They were using outdated atari processing stuff

louchenyao commented 6 years ago

By the way, I can’t find the auto saved model since I trained it by myself. Does anyone have same problem?

zwfcrazy commented 6 years ago

@Chenyao2333 read the code, somehow it's been commented out.

    act = deepq.learn(
        env,
        q_func=model,
        lr=1e-4,
        max_timesteps=args.num_timesteps,
        buffer_size=10000,
        exploration_fraction=0.1,
        exploration_final_eps=0.01,
        train_freq=4,
        learning_starts=10000,
        target_network_update_freq=1000,
        gamma=0.99,
        prioritized_replay=bool(args.prioritized)
    )
    # act.save("pong_model.pkl") XXX
    env.close()