hongshaorou/Tianshou
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
Tianshou/examples/atari/atari_rainbow.py
Michael Panchenko 07702fc007
Improved typing and reduced duplication (#912) 
# Goals of the PR

The PR introduces **no changes to functionality**, apart from improved
input validation here and there. The main goals are to reduce some
complexity of the code, to improve types and IDE completions, and to
extend documentation and block comments where appropriate. Because of
the change to the trainer interfaces, many files are affected (more
details below), but still the overall changes are "small" in a certain
sense.

## Major Change 1 - BatchProtocol

**TL;DR:** One can now annotate which fields the batch is expected to
have on input params and which fields a returned batch has. Should be
useful for reading the code. getting meaningful IDE support, and
catching bugs with mypy. This annotation strategy will continue to work
if Batch is replaced by TensorDict or by something else.

**In more detail:** Batch itself has no fields and using it for
annotations is of limited informational power. Batches with fields are
not separate classes but instead instances of Batch directly, so there
is no type that could be used for annotation. Fortunately, python
`Protocol` is here for the rescue. With these changes we can now do
things like

```python
class ActionBatchProtocol(BatchProtocol):
    logits: Sequence[Union[tuple, torch.Tensor]]
    dist: torch.distributions.Distribution
    act: torch.Tensor
    state: Optional[torch.Tensor]


class RolloutBatchProtocol(BatchProtocol):
    obs: torch.Tensor
    obs_next: torch.Tensor
    info: Dict[str, Any]
    rew: torch.Tensor
    terminated: torch.Tensor
    truncated: torch.Tensor

class PGPolicy(BasePolicy):
    ...

    def forward(
        self,
        batch: RolloutBatchProtocol,
        state: Optional[Union[dict, Batch, np.ndarray]] = None,
        **kwargs: Any,
    ) -> ActionBatchProtocol:

```

The IDE and mypy are now very helpful in finding errors and in
auto-completion, whereas before the tools couldn't assist in that at
all.

## Major Change 2 - remove duplication in trainer package

**TL;DR:** There was a lot of duplication between `BaseTrainer` and its
subclasses. Even worse, it was almost-duplication. There was also
interface fragmentation through things like `onpolicy_trainer`. Now this
duplication is gone and all downstream code was adjusted.

**In more detail:** Since this change affects a lot of code, I would
like to explain why I thought it to be necessary.

1. The subclasses of `BaseTrainer` just duplicated docstrings and
constructors. What's worse, they changed the order of args there, even
turning some kwargs of BaseTrainer into args. They also had the arg
`learning_type` which was passed as kwarg to the base class and was
unused there. This made things difficult to maintain, and in fact some
errors were already present in the duplicated docstrings.
2. The "functions" a la `onpolicy_trainer`, which just called the
`OnpolicyTrainer.run`, not only introduced interface fragmentation but
also completely obfuscated the docstring and interfaces. They themselves
had no dosctring and the interface was just `*args, **kwargs`, which
makes it impossible to understand what they do and which things can be
passed without reading their implementation, then reading the docstring
of the associated class, etc. Needless to say, mypy and IDEs provide no
support with such functions. Nevertheless, they were used everywhere in
the code-base. I didn't find the sacrifices in clarity and complexity
justified just for the sake of not having to write `.run()` after
instantiating a trainer.
3. The trainers are all very similar to each other. As for my
application I needed a new trainer, I wanted to understand their
structure. The similarity, however, was hard to discover since they were
all in separate modules and there was so much duplication. I kept
staring at the constructors for a while until I figured out that
essentially no changes to the superclass were introduced. Now they are
all in the same module and the similarities/differences between them are
much easier to grasp (in my opinion)
4. Because of (1), I had to manually change and check a lot of code,
which was very tedious and boring. This kind of work won't be necessary
in the future, since now IDEs can be used for changing signatures,
renaming args and kwargs, changing class names and so on.

I have some more reasons, but maybe the above ones are convincing
enough.

## Minor changes: improved input validation and types

I added input validation for things like `state` and `action_scaling`
(which only makes sense for continuous envs). After adding this, some
tests failed to pass this validation. There I added
`action_scaling=isinstance(env.action_space, Box)`, after which tests
were green. I don't know why the tests were green before, since action
scaling doesn't make sense for discrete actions. I guess some aspect was
not tested and didn't crash.

I also added Literal in some places, in particular for
`action_bound_method`. Now it is no longer allowed to pass an empty
string, instead one should pass `None`. Also here there is input
validation with clear error messages.

@Trinkle23897 The functional tests are green. I didn't want to fix the
formatting, since it will change in the next PR that will solve #914
anyway. I also found a whole bunch of code in `docs/_static`, which I
just deleted (shouldn't it be copied from the sources during docs build
instead of committed?). I also haven't adjusted the documentation yet,
which atm still mentions the trainers of the type
`onpolicy_trainer(...)` instead of `OnpolicyTrainer(...).run()`

## Breaking Changes

The adjustments to the trainer package introduce breaking changes as
duplicated interfaces are deleted. However, it should be very easy for
users to adjust to them

---------

Co-authored-by: Michael Panchenko <m.panchenko@appliedai.de>
2023-08-22 09:54:46 -07:00

259 lines
9.4 KiB
Python
Raw Blame History

import argparse
import datetime
import os
import pprint
import numpy as np
import torch
from atari_network import Rainbow
from atari_wrapper import make_atari_env
from torch.utils.tensorboard import SummaryWriter
from tianshou.data import Collector, PrioritizedVectorReplayBuffer, VectorReplayBuffer
from tianshou.policy import RainbowPolicy
from tianshou.trainer import OffpolicyTrainer
from tianshou.utils import TensorboardLogger, WandbLogger
def get_args():
parser = argparse.ArgumentParser()
parser.add_argument("--task", type=str, default="PongNoFrameskip-v4")
parser.add_argument("--seed", type=int, default=0)
parser.add_argument("--scale-obs", type=int, default=0)
parser.add_argument("--eps-test", type=float, default=0.005)
parser.add_argument("--eps-train", type=float, default=1.)
parser.add_argument("--eps-train-final", type=float, default=0.05)
parser.add_argument("--buffer-size", type=int, default=100000)
parser.add_argument("--lr", type=float, default=0.0000625)
parser.add_argument("--gamma", type=float, default=0.99)
parser.add_argument("--num-atoms", type=int, default=51)
parser.add_argument("--v-min", type=float, default=-10.)
parser.add_argument("--v-max", type=float, default=10.)
parser.add_argument("--noisy-std", type=float, default=0.1)
parser.add_argument("--no-dueling", action="store_true", default=False)
parser.add_argument("--no-noisy", action="store_true", default=False)
parser.add_argument("--no-priority", action="store_true", default=False)
parser.add_argument("--alpha", type=float, default=0.5)
parser.add_argument("--beta", type=float, default=0.4)
parser.add_argument("--beta-final", type=float, default=1.)
parser.add_argument("--beta-anneal-step", type=int, default=5000000)
parser.add_argument("--no-weight-norm", action="store_true", default=False)
parser.add_argument("--n-step", type=int, default=3)
parser.add_argument("--target-update-freq", type=int, default=500)
parser.add_argument("--epoch", type=int, default=100)
parser.add_argument("--step-per-epoch", type=int, default=100000)
parser.add_argument("--step-per-collect", type=int, default=10)
parser.add_argument("--update-per-step", type=float, default=0.1)
parser.add_argument("--batch-size", type=int, default=32)
parser.add_argument("--training-num", type=int, default=10)
parser.add_argument("--test-num", type=int, default=10)
parser.add_argument("--logdir", type=str, default="log")
parser.add_argument("--render", type=float, default=0.)
parser.add_argument(
"--device", type=str, default="cuda" if torch.cuda.is_available() else "cpu"
)
parser.add_argument("--frames-stack", type=int, default=4)
parser.add_argument("--resume-path", type=str, default=None)
parser.add_argument("--resume-id", type=str, default=None)
parser.add_argument(
"--logger",
type=str,
default="tensorboard",
choices=["tensorboard", "wandb"],
)
parser.add_argument("--wandb-project", type=str, default="atari.benchmark")
parser.add_argument(
"--watch",
default=False,
action="store_true",
help="watch the play of pre-trained policy only"
)
parser.add_argument("--save-buffer-name", type=str, default=None)
return parser.parse_args()
def test_rainbow(args=get_args()):
env, train_envs, test_envs = make_atari_env(
args.task,
args.seed,
args.training_num,
args.test_num,
scale=args.scale_obs,
frame_stack=args.frames_stack,
)
args.state_shape = env.observation_space.shape or env.observation_space.n
args.action_shape = env.action_space.shape or env.action_space.n
# should be N_FRAMES x H x W
print("Observations shape:", args.state_shape)
print("Actions shape:", args.action_shape)
# seed
np.random.seed(args.seed)
torch.manual_seed(args.seed)
# define model
net = Rainbow(
*args.state_shape,
args.action_shape,
args.num_atoms,
args.noisy_std,
args.device,
is_dueling=not args.no_dueling,
is_noisy=not args.no_noisy
)
optim = torch.optim.Adam(net.parameters(), lr=args.lr)
# define policy
policy = RainbowPolicy(
net,
optim,
args.gamma,
args.num_atoms,
args.v_min,
args.v_max,
args.n_step,
target_update_freq=args.target_update_freq
).to(args.device)
# load a previous policy
if args.resume_path:
policy.load_state_dict(torch.load(args.resume_path, map_location=args.device))
print("Loaded agent from: ", args.resume_path)
# replay buffer: `save_last_obs` and `stack_num` can be removed together
# when you have enough RAM
if args.no_priority:
buffer = VectorReplayBuffer(
args.buffer_size,
buffer_num=len(train_envs),
ignore_obs_next=True,
save_only_last_obs=True,
stack_num=args.frames_stack
)
else:
buffer = PrioritizedVectorReplayBuffer(
args.buffer_size,
buffer_num=len(train_envs),
ignore_obs_next=True,
save_only_last_obs=True,
stack_num=args.frames_stack,
alpha=args.alpha,
beta=args.beta,
weight_norm=not args.no_weight_norm
)
# collector
train_collector = Collector(policy, train_envs, buffer, exploration_noise=True)
test_collector = Collector(policy, test_envs, exploration_noise=True)
# log
now = datetime.datetime.now().strftime("%y%m%d-%H%M%S")
args.algo_name = "rainbow"
log_name = os.path.join(args.task, args.algo_name, str(args.seed), now)
log_path = os.path.join(args.logdir, log_name)
# logger
if args.logger == "wandb":
logger = WandbLogger(
save_interval=1,
name=log_name.replace(os.path.sep, "__"),
run_id=args.resume_id,
config=args,
project=args.wandb_project,
)
writer = SummaryWriter(log_path)
writer.add_text("args", str(args))
if args.logger == "tensorboard":
logger = TensorboardLogger(writer)
else: # wandb
logger.load(writer)
def save_best_fn(policy):
torch.save(policy.state_dict(), os.path.join(log_path, "policy.pth"))
def stop_fn(mean_rewards):
if env.spec.reward_threshold:
return mean_rewards >= env.spec.reward_threshold
elif "Pong" in args.task:
return mean_rewards >= 20
else:
return False
def train_fn(epoch, env_step):
# nature DQN setting, linear decay in the first 1M steps
if env_step <= 1e6:
eps = args.eps_train - env_step / 1e6 * \
(args.eps_train - args.eps_train_final)
else:
eps = args.eps_train_final
policy.set_eps(eps)
if env_step % 1000 == 0:
logger.write("train/env_step", env_step, {"train/eps": eps})
if not args.no_priority:
if env_step <= args.beta_anneal_step:
beta = args.beta - env_step / args.beta_anneal_step * \
(args.beta - args.beta_final)
else:
beta = args.beta_final
buffer.set_beta(beta)
if env_step % 1000 == 0:
logger.write("train/env_step", env_step, {"train/beta": beta})
def test_fn(epoch, env_step):
policy.set_eps(args.eps_test)
# watch agent's performance
def watch():
print("Setup test envs ...")
policy.eval()
policy.set_eps(args.eps_test)
test_envs.seed(args.seed)
if args.save_buffer_name:
print(f"Generate buffer with size {args.buffer_size}")
buffer = PrioritizedVectorReplayBuffer(
args.buffer_size,
buffer_num=len(test_envs),
ignore_obs_next=True,
save_only_last_obs=True,
stack_num=args.frames_stack,
alpha=args.alpha,
beta=args.beta
)
collector = Collector(policy, test_envs, buffer, exploration_noise=True)
result = collector.collect(n_step=args.buffer_size)
print(f"Save buffer into {args.save_buffer_name}")
# Unfortunately, pickle will cause oom with 1M buffer size
buffer.save_hdf5(args.save_buffer_name)
else:
print("Testing agent ...")
test_collector.reset()
result = test_collector.collect(n_episode=args.test_num, render=args.render)
rew = result["rews"].mean()
print(f"Mean reward (over {result['n/ep']} episodes): {rew}")
if args.watch:
watch()
exit(0)
# test train_collector and start filling replay buffer
train_collector.collect(n_step=args.batch_size * args.training_num)
# trainer
result = OffpolicyTrainer(
policy=policy,
train_collector=train_collector,
test_collector=test_collector,
max_epoch=args.epoch,
step_per_epoch=args.step_per_epoch,
step_per_collect=args.step_per_collect,
episode_per_test=args.test_num,
batch_size=args.batch_size,
train_fn=train_fn,
test_fn=test_fn,
stop_fn=stop_fn,
save_best_fn=save_best_fn,
logger=logger,
update_per_step=args.update_per_step,
test_in_train=False,
).run()
pprint.pprint(result)
watch()
if __name__ == "__main__":
test_rainbow(get_args())
Reference in New Issue View Git Blame Copy Permalink