- [x] I have marked all applicable categories:
+ [ ] exception-raising fix
+ [x] algorithm implementation fix
+ [ ] documentation modification
+ [ ] new feature
- [x] I have reformatted the code using `make format` (**required**)
- [x] I have checked the code using `make commit-checks` (**required**)
- [x] If applicable, I have mentioned the relevant/related issue(s)
- [x] If applicable, I have listed every items in this Pull Request
below
While trying to debug Atari PPO+LSTM, I found significant gap between
our Atari PPO example vs [CleanRL's Atari PPO w/
EnvPool](https://docs.cleanrl.dev/rl-algorithms/ppo/#ppo_atari_envpoolpy).
I tried to align our implementation with CleaRL's version, mostly in
hyper parameter choices, and got significant gain in Breakout, Qbert,
SpaceInvaders while on par in other games. After this fix, I would
suggest updating our [Atari
Benchmark](https://tianshou.readthedocs.io/en/master/tutorials/benchmark.html)
PPO experiments.
A few interesting findings:
- Layer initialization helps stabilize the training and enable the use
of larger learning rates; without it, larger learning rates will trigger
NaN gradient very quickly;
- ppo.py#L97-L101: this change helps training stability for reasons I do
not understand; also it makes the GPU usage higher.
Shoutout to [CleanRL](https://github.com/vwxyzjn/cleanrl) for a
well-tuned Atari PPO reference implementation!
This is the PR for QR-DQN algorithm: https://arxiv.org/abs/1710.10044
1. add QR-DQN policy in tianshou/policy/modelfree/qrdqn.py.
2. add QR-DQN net in examples/atari/atari_network.py.
3. add QR-DQN atari example in examples/atari/atari_qrdqn.py.
4. add QR-DQN statement in tianshou/policy/init.py.
5. add QR-DQN unit test in test/discrete/test_qrdqn.py.
6. add QR-DQN atari results in examples/atari/results/qrdqn/.
7. add compute_q_value in DQNPolicy and C51Policy for simplify forward function.
8. move `with torch.no_grad():` from `_target_q` to BasePolicy
By running "python3 atari_qrdqn.py --task "PongNoFrameskip-v4" --batch-size 64", get best_result': '19.8 ± 0.40', in epoch 8.
This is the PR for C51algorithm: https://arxiv.org/abs/1707.06887
1. add C51 policy in tianshou/policy/modelfree/c51.py.
2. add C51 net in tianshou/utils/net/discrete.py.
3. add C51 atari example in examples/atari/atari_c51.py.
4. add C51 statement in tianshou/policy/__init__.py.
5. add C51 test in test/discrete/test_c51.py.
6. add C51 atari results in examples/atari/results/c51/.
By running "python3 atari_c51.py --task "PongNoFrameskip-v4" --batch-size 64", get best_result': '20.50 ± 0.50', in epoch 9.
By running "python3 atari_c51.py --task "BreakoutNoFrameskip-v4" --n-step 1 --epoch 40", get best_reward: 407.400000 ± 31.155096 in epoch 39.
This PR aims to provide the script of Atari DQN setting:
- A speedrun of PongNoFrameskip-v4 (finished, about half an hour in i7-8750 + GTX1060 with 1M environment steps)
- A general script for all atari game
Since we use multiple env for simulation, the result is slightly different from the original paper, but consider to be acceptable.
It also adds another parameter save_only_last_obs for replay buffer in order to save the memory.
Co-authored-by: Trinkle23897 <463003665@qq.com>
