522f7fbf98
This PR adds strict typing to the output of `update` and `learn` in all
policies. This will likely be the last large refactoring PR before the
next release (0.6.0, not 1.0.0), so it requires some attention. Several
difficulties were encountered on the path to that goal:
1. The policy hierarchy is actually "broken" in the sense that the keys
of dicts that were output by `learn` did not follow the same enhancement
(inheritance) pattern as the policies. This is a real problem and should
be addressed in the near future. Generally, several aspects of the
policy design and hierarchy might deserve a dedicated discussion.
2. Each policy needs to be generic in the stats return type, because one
might want to extend it at some point and then also extend the stats.
Even within the source code base this pattern is necessary in many
places.
3. The interaction between learn and update is a bit quirky, we
currently handle it by having update modify special field inside
TrainingStats, whereas all other fields are handled by learn.
4. The IQM module is a policy wrapper and required a
TrainingStatsWrapper. The latter relies on a bunch of black magic.
They were addressed by:
1. Live with the broken hierarchy, which is now made visible by bounds
in generics. We use type: ignore where appropriate.
2. Make all policies generic with bounds following the policy
inheritance hierarchy (which is incorrect, see above). We experimented a
bit with nested TrainingStats classes, but that seemed to add more
complexity and be harder to understand. Unfortunately, mypy thinks that
the code below is wrong, wherefore we have to add `type: ignore` to the
return of each `learn`
```python
T = TypeVar("T", bound=int)
def f() -> T:
return 3
```
3. See above
4. Write representative tests for the `TrainingStatsWrapper`. Still, the
black magic might cause nasty surprises down the line (I am not proud of
it)...
Closes #933
---------
Co-authored-by: Maximilian Huettenrauch <m.huettenrauch@appliedai.de>
Co-authored-by: Michael Panchenko <m.panchenko@appliedai.de>
ViZDoom
ViZDoom is a popular RL env for a famous first-person shooting game Doom. Here we provide some results and intuitions for this scenario.
EnvPool
We highly recommend using envpool to run the following experiments. To install, in a linux machine, type:
pip install envpool
After that, make_vizdoom_env will automatically switch to envpool's ViZDoom env. EnvPool's implementation is much faster (about 2~3x faster for pure execution speed, 1.5x for overall RL training pipeline) than python vectorized env implementation.
For more information, please refer to EnvPool's GitHub and Docs.
Train
To train an agent:
python3 vizdoom_c51.py --task {D1_basic|D2_navigation|D3_battle|D4_battle2}
D1 (health gathering) should finish training (no death) in less than 500k env step (5 epochs);
D3 can reach 1600+ reward (75+ killcount in 5 minutes);
D4 can reach 700+ reward. Here is the result:
(episode length, the maximum length is 2625 because we use frameskip=4, that is 10500/4=2625)
(episode reward)
To evaluate an agent's performance:
python3 vizdoom_c51.py --test-num 100 --resume-path policy.pth --watch --task {D1_basic|D3_battle|D4_battle2}
To save .lmp files for recording:
python3 vizdoom_c51.py --save-lmp --test-num 100 --resume-path policy.pth --watch --task {D1_basic|D3_battle|D4_battle2}
it will store lmp file in lmps/ directory. To watch these lmp files (for example, d3 lmp):
python3 replay.py maps/D3_battle.cfg episode_8_25.lmp
We provide two lmp files (d3 best and d4 best) under results/c51, you can use the following command to enjoy:
python3 replay.py maps/D3_battle.cfg results/c51/d3.lmp
python3 replay.py maps/D4_battle2.cfg results/c51/d4.lmp
Maps
See maps/README.md
Reward
- living reward is bad
- combo-action is really important
- negative reward for health and ammo2 is really helpful for d3/d4
- only with positive reward for health is really helpful for d1
- remove MOVE_BACKWARD may converge faster but the final performance may be lower
Algorithms
The setting is exactly the same as Atari. You can definitely try more algorithms listed in Atari example.
C51 (single run)
| task | best reward | reward curve | parameters |
|---|---|---|---|
| D2_navigation | 747.52 |  |
python3 vizdoom_c51.py --task "D2_navigation" |
| D3_battle | 1855.29 |  |
python3 vizdoom_c51.py --task "D3_battle" |
PPO (single run)
| task | best reward | reward curve | parameters |
|---|---|---|---|
| D2_navigation | 770.75 |  |
python3 vizdoom_ppo.py --task "D2_navigation" |
| D3_battle | 320.59 |  |
python3 vizdoom_ppo.py --task "D3_battle" |
PPO with ICM (single run)
| task | best reward | reward curve | parameters |
|---|---|---|---|
| D2_navigation | 844.99 |  |
python3 vizdoom_ppo.py --task "D2_navigation" --icm-lr-scale 10 |
| D3_battle | 547.08 |  |
python3 vizdoom_ppo.py --task "D3_battle" --icm-lr-scale 10 |