File size: 8,365 Bytes
e491716
 
2a8bf2e
e491716
0b59ac1
 
 
e491716
 
2a8bf2e
e491716
 
0b59ac1
e491716
 
 
 
 
 
 
 
 
 
 
0b59ac1
e491716
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0b59ac1
e491716
0b59ac1
 
 
e491716
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0b59ac1
2a8bf2e
e491716
 
 
 
 
0b59ac1
 
 
 
 
e491716
 
 
2a8bf2e
e491716
0b59ac1
 
 
2a8bf2e
0b59ac1
 
 
e491716
 
2a8bf2e
 
 
 
e491716
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0b59ac1
2a8bf2e
 
e491716
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0b59ac1
2a8bf2e
 
e491716
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0b59ac1
2a8bf2e
e491716
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2a8bf2e
 
 
 
 
 
 
 
 
e491716
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2a8bf2e
e491716
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
import itertools
import os
import shutil
from time import perf_counter
from typing import Dict, List, Optional, Union

import numpy as np
from torch.utils.tensorboard.writer import SummaryWriter

from rl_algo_impls.shared.callbacks import Callback
from rl_algo_impls.shared.policy.policy import Policy
from rl_algo_impls.shared.stats import Episode, EpisodeAccumulator, EpisodesStats
from rl_algo_impls.wrappers.action_mask_wrapper import find_action_masker
from rl_algo_impls.wrappers.vec_episode_recorder import VecEpisodeRecorder
from rl_algo_impls.wrappers.vectorable_wrapper import VecEnv


class EvaluateAccumulator(EpisodeAccumulator):
    def __init__(
        self,
        num_envs: int,
        goal_episodes: int,
        print_returns: bool = True,
        ignore_first_episode: bool = False,
        additional_keys_to_log: Optional[List[str]] = None,
    ):
        super().__init__(num_envs)
        self.completed_episodes_by_env_idx = [[] for _ in range(num_envs)]
        self.goal_episodes_per_env = int(np.ceil(goal_episodes / num_envs))
        self.print_returns = print_returns
        if ignore_first_episode:
            first_done = set()

            def should_record_done(idx: int) -> bool:
                has_done_first_episode = idx in first_done
                first_done.add(idx)
                return has_done_first_episode

            self.should_record_done = should_record_done
        else:
            self.should_record_done = lambda idx: True
        self.additional_keys_to_log = additional_keys_to_log

    def on_done(self, ep_idx: int, episode: Episode, info: Dict) -> None:
        if self.additional_keys_to_log:
            episode.info = {k: info[k] for k in self.additional_keys_to_log}
        if (
            self.should_record_done(ep_idx)
            and len(self.completed_episodes_by_env_idx[ep_idx])
            >= self.goal_episodes_per_env
        ):
            return
        self.completed_episodes_by_env_idx[ep_idx].append(episode)
        if self.print_returns:
            print(
                f"Episode {len(self)} | "
                f"Score {episode.score} | "
                f"Length {episode.length}"
            )

    def __len__(self) -> int:
        return sum(len(ce) for ce in self.completed_episodes_by_env_idx)

    @property
    def episodes(self) -> List[Episode]:
        return list(itertools.chain(*self.completed_episodes_by_env_idx))

    def is_done(self) -> bool:
        return all(
            len(ce) == self.goal_episodes_per_env
            for ce in self.completed_episodes_by_env_idx
        )


def evaluate(
    env: VecEnv,
    policy: Policy,
    n_episodes: int,
    render: bool = False,
    deterministic: bool = True,
    print_returns: bool = True,
    ignore_first_episode: bool = False,
    additional_keys_to_log: Optional[List[str]] = None,
    score_function: str = "mean-std",
) -> EpisodesStats:
    policy.sync_normalization(env)
    policy.eval()

    episodes = EvaluateAccumulator(
        env.num_envs,
        n_episodes,
        print_returns,
        ignore_first_episode,
        additional_keys_to_log=additional_keys_to_log,
    )

    obs = env.reset()
    get_action_mask = getattr(env, "get_action_mask", None)
    while not episodes.is_done():
        act = policy.act(
            obs,
            deterministic=deterministic,
            action_masks=get_action_mask() if get_action_mask else None,
        )
        obs, rew, done, info = env.step(act)
        episodes.step(rew, done, info)
        if render:
            env.render()
    stats = EpisodesStats(
        episodes.episodes,
        score_function=score_function,
    )
    if print_returns:
        print(stats)
    return stats


class EvalCallback(Callback):
    def __init__(
        self,
        policy: Policy,
        env: VecEnv,
        tb_writer: SummaryWriter,
        best_model_path: Optional[str] = None,
        step_freq: Union[int, float] = 50_000,
        n_episodes: int = 10,
        save_best: bool = True,
        deterministic: bool = True,
        record_best_videos: bool = True,
        video_env: Optional[VecEnv] = None,
        best_video_dir: Optional[str] = None,
        max_video_length: int = 3600,
        ignore_first_episode: bool = False,
        additional_keys_to_log: Optional[List[str]] = None,
        score_function: str = "mean-std",
        wandb_enabled: bool = False,
    ) -> None:
        super().__init__()
        self.policy = policy
        self.env = env
        self.tb_writer = tb_writer
        self.best_model_path = best_model_path
        self.step_freq = int(step_freq)
        self.n_episodes = n_episodes
        self.save_best = save_best
        self.deterministic = deterministic
        self.stats: List[EpisodesStats] = []
        self.best = None

        self.record_best_videos = record_best_videos
        assert video_env or not record_best_videos
        self.video_env = video_env
        assert best_video_dir or not record_best_videos
        self.best_video_dir = best_video_dir
        if best_video_dir:
            os.makedirs(best_video_dir, exist_ok=True)
        self.max_video_length = max_video_length
        self.best_video_base_path = None
        self.ignore_first_episode = ignore_first_episode
        self.additional_keys_to_log = additional_keys_to_log
        self.score_function = score_function
        self.wandb_enabled = wandb_enabled

    def on_step(self, timesteps_elapsed: int = 1) -> bool:
        super().on_step(timesteps_elapsed)
        if self.timesteps_elapsed // self.step_freq >= len(self.stats):
            self.evaluate()
        return True

    def evaluate(
        self, n_episodes: Optional[int] = None, print_returns: Optional[bool] = None
    ) -> EpisodesStats:
        start_time = perf_counter()
        eval_stat = evaluate(
            self.env,
            self.policy,
            n_episodes or self.n_episodes,
            deterministic=self.deterministic,
            print_returns=print_returns or False,
            ignore_first_episode=self.ignore_first_episode,
            additional_keys_to_log=self.additional_keys_to_log,
            score_function=self.score_function,
        )
        end_time = perf_counter()
        self.tb_writer.add_scalar(
            "eval/steps_per_second",
            eval_stat.length.sum() / (end_time - start_time),
            self.timesteps_elapsed,
        )
        self.policy.train(True)
        print(f"Eval Timesteps: {self.timesteps_elapsed} | {eval_stat}")

        self.stats.append(eval_stat)

        if not self.best or eval_stat >= self.best:
            strictly_better = not self.best or eval_stat > self.best
            self.best = eval_stat
            if self.save_best:
                assert self.best_model_path
                self.policy.save(self.best_model_path)
                print("Saved best model")
                if self.wandb_enabled:
                    import wandb

                    best_model_name = os.path.split(self.best_model_path)[-1]
                    shutil.make_archive(
                        os.path.join(wandb.run.dir, best_model_name),  # type: ignore
                        "zip",
                        self.best_model_path,
                    )
            self.best.write_to_tensorboard(
                self.tb_writer, "best_eval", self.timesteps_elapsed
            )
            if strictly_better and self.record_best_videos:
                assert self.video_env and self.best_video_dir
                self.best_video_base_path = os.path.join(
                    self.best_video_dir, str(self.timesteps_elapsed)
                )
                video_wrapped = VecEpisodeRecorder(
                    self.video_env,
                    self.best_video_base_path,
                    max_video_length=self.max_video_length,
                )
                video_stats = evaluate(
                    video_wrapped,
                    self.policy,
                    1,
                    deterministic=self.deterministic,
                    print_returns=False,
                    score_function=self.score_function,
                )
                print(f"Saved best video: {video_stats}")

        eval_stat.write_to_tensorboard(self.tb_writer, "eval", self.timesteps_elapsed)

        return eval_stat