ding.bonus.ddpg

ding.bonus.ddpg

DDPGAgent

Overview

Class of agent for training, evaluation and deployment of Reinforcement learning algorithm Deep Deterministic Policy Gradient(DDPG). For more information about the system design of RL agent, please refer to https://di-engine-docs.readthedocs.io/en/latest/03_system/agent.html.

Interface: __init__, train, deploy, collect_data, batch_evaluate, best

supported_env_list = list(supported_env_cfg.keys()) class-attribute instance-attribute

Overview

List of supported envs.

Examples: >>> from ding.bonus.ddpg import DDPGAgent >>> print(DDPGAgent.supported_env_list)

best property

Overview

Load the best model from the checkpoint directory, which is by default in folder exp_name/ckpt/eval.pth.tar. The return value is the agent with the best model.

Returns: - (:obj:DDPGAgent): The agent with the best model. Examples: >>> agent = DDPGAgent(env_id='LunarLanderContinuous-v2') >>> agent.train() >>> agent = agent.best

.. note:: The best model is the model with the highest evaluation return. If this method is called, the current model will be replaced by the best model.

__init__(env_id=None, env=None, seed=0, exp_name=None, model=None, cfg=None, policy_state_dict=None)

Overview

Initialize agent for DDPG algorithm.

Arguments: - env_id (:obj:str): The environment id, which is a registered environment name in gym or gymnasium. If env_id is not specified, env_id in cfg.env must be specified. If env_id is specified, env_id in cfg.env will be ignored. env_id should be one of the supported envs, which can be found in supported_env_list. - env (:obj:BaseEnv): The environment instance for training and evaluation. If env is not specified, env_id`` or ``cfg.env.env_id`` must be specified. ``env_id`` or ``cfg.env.env_id`` will be used to create environment instance. If ``env`` is specified, ``env_id`` and ``cfg.env.env_id`` will be ignored. - seed (:obj:int): The random seed, which is set before running the program. Default to 0. - exp_name (:obj:str): The name of this experiment, which will be used to create the folder to save log data. Default to None. If not specified, the folder name will be ``env_id``-``algorithm``. - model (:obj:torch.nn.Module): The model of DDPG algorithm, which should be an instance of class :class:ding.model.ContinuousQAC. If not specified, a default model will be generated according to the configuration. - cfg (:obj:Union[EasyDict, dict]): The configuration of DDPG algorithm, which is a dict. Default to None. If not specified, the default configuration will be used. The default configuration can be found in ``ding/config/example/DDPG/gym_lunarlander_v2.py``. - policy_state_dict (:obj:str`): The path of policy state dict saved by PyTorch a in local file. If specified, the policy will be loaded from this file. Default to None.

.. note:: An RL Agent Instance can be initialized in two basic ways. For example, we have an environment with id LunarLanderContinuous-v2 registered in gym, and we want to train an agent with DDPG algorithm with default configuration. Then we can initialize the agent in the following ways: >>> agent = DDPGAgent(env_id='LunarLanderContinuous-v2') or, if we want can specify the env_id in the configuration: >>> cfg = {'env': {'env_id': 'LunarLanderContinuous-v2'}, 'policy': ...... } >>> agent = DDPGAgent(cfg=cfg) There are also other arguments to specify the agent when initializing. For example, if we want to specify the environment instance: >>> env = CustomizedEnv('LunarLanderContinuous-v2') >>> agent = DDPGAgent(cfg=cfg, env=env) or, if we want to specify the model: >>> model = ContinuousQAC(**cfg.policy.model) >>> agent = DDPGAgent(cfg=cfg, model=model) or, if we want to reload the policy from a saved policy state dict: >>> agent = DDPGAgent(cfg=cfg, policy_state_dict='LunarLanderContinuous-v2.pth.tar') Make sure that the configuration is consistent with the saved policy state dict.

train(step=int(10000000.0), collector_env_num=None, evaluator_env_num=None, n_iter_log_show=500, n_iter_save_ckpt=1000, context=None, debug=False, wandb_sweep=False)

Overview

Train the agent with DDPG algorithm for step iterations with collector_env_num collector environments and evaluator_env_num evaluator environments. Information during training will be recorded and saved by wandb.

Arguments: - step (:obj:int): The total training environment steps of all collector environments. Default to 1e7. - collector_env_num (:obj:int): The collector environment number. Default to None. If not specified, it will be set according to the configuration. - evaluator_env_num (:obj:int): The evaluator environment number. Default to None. If not specified, it will be set according to the configuration. - n_iter_save_ckpt (:obj:int): The frequency of saving checkpoint every training iteration. Default to 1000. - context (:obj:str): The multi-process context of the environment manager. Default to None. It can be specified as spawn, fork or forkserver. - debug (:obj:bool): Whether to use debug mode in the environment manager. Default to False. If set True, base environment manager will be used for easy debugging. Otherwise, subprocess environment manager will be used. - wandb_sweep (:obj:bool): Whether to use wandb sweep, which is a hyper-parameter optimization process for seeking the best configurations. Default to False. If True, the wandb sweep id will be used as the experiment name. Returns: - (:obj:TrainingReturn): The training result, of which the attributions are: - wandb_url (:obj:str): The weight & biases (wandb) project url of the trainning experiment.

deploy(enable_save_replay=False, concatenate_all_replay=False, replay_save_path=None, seed=None, debug=False)

Overview

Deploy the agent with DDPG algorithm by interacting with the environment, during which the replay video can be saved if enable_save_replay is True. The evaluation result will be returned.

Arguments: - enable_save_replay (:obj:bool): Whether to save the replay video. Default to False. - concatenate_all_replay (:obj:bool): Whether to concatenate all replay videos into one video. Default to False. If enable_save_replay is False, this argument will be ignored. If enable_save_replay is True and concatenate_all_replay is False, the replay video of each episode will be saved separately. - replay_save_path (:obj:str): The path to save the replay video. Default to None. If not specified, the video will be saved in exp_name/videos. - seed (:obj:Union[int, List]): The random seed, which is set before running the program. Default to None. If not specified, self.seed will be used. If seed is an integer, the agent will be deployed once. If seed is a list of integers, the agent will be deployed once for each seed in the list. - debug (:obj:bool): Whether to use debug mode in the environment manager. Default to False. If set True, base environment manager will be used for easy debugging. Otherwise, subprocess environment manager will be used. Returns: - (:obj:EvalReturn): The evaluation result, of which the attributions are: - eval_value (:obj:np.float32): The mean of evaluation return. - eval_value_std (:obj:np.float32): The standard deviation of evaluation return.

collect_data(env_num=8, save_data_path=None, n_sample=None, n_episode=None, context=None, debug=False)

Overview

Collect data with DDPG algorithm for n_episode episodes with env_num collector environments. The collected data will be saved in save_data_path if specified, otherwise it will be saved in exp_name/demo_data.

Arguments: - env_num (:obj:int): The number of collector environments. Default to 8. - save_data_path (:obj:str): The path to save the collected data. Default to None. If not specified, the data will be saved in exp_name/demo_data. - n_sample (:obj:int): The number of samples to collect. Default to None. If not specified, n_episode must be specified. - n_episode (:obj:int): The number of episodes to collect. Default to None. If not specified, n_sample must be specified. - context (:obj:str): The multi-process context of the environment manager. Default to None. It can be specified as spawn, fork or forkserver. - debug (:obj:bool): Whether to use debug mode in the environment manager. Default to False. If set True, base environment manager will be used for easy debugging. Otherwise, subprocess environment manager will be used.

batch_evaluate(env_num=4, n_evaluator_episode=4, context=None, debug=False)

Overview

Evaluate the agent with DDPG algorithm for n_evaluator_episode episodes with env_num evaluator environments. The evaluation result will be returned. The difference between methods batch_evaluate and deploy is that batch_evaluate will create multiple evaluator environments to evaluate the agent to get an average performance, while deploy will only create one evaluator environment to evaluate the agent and save the replay video.

Arguments: - env_num (:obj:int): The number of evaluator environments. Default to 4. - n_evaluator_episode (:obj:int): The number of episodes to evaluate. Default to 4. - context (:obj:str): The multi-process context of the environment manager. Default to None. It can be specified as spawn, fork or forkserver. - debug (:obj:bool): Whether to use debug mode in the environment manager. Default to False. If set True, base environment manager will be used for easy debugging. Otherwise, subprocess environment manager will be used. Returns: - (:obj:EvalReturn): The evaluation result, of which the attributions are: - eval_value (:obj:np.float32): The mean of evaluation return. - eval_value_std (:obj:np.float32): The standard deviation of evaluation return.

Full Source Code

../ding/bonus/ddpg.py

1from typing import Optional, Union, List 2from ditk import logging 3from easydict import EasyDict 4import os 5import numpy as np 6import torch 7import treetensor.torch as ttorch 8from ding.framework import task, OnlineRLContext 9from ding.framework.middleware import CkptSaver, \ 10 wandb_online_logger, offline_data_saver, termination_checker, interaction_evaluator, StepCollector, data_pusher, \ 11 OffPolicyLearner, final_ctx_saver 12from ding.envs import BaseEnv 13from ding.envs import setup_ding_env_manager 14from ding.policy import DDPGPolicy 15from ding.utils import set_pkg_seed 16from ding.utils import get_env_fps, render 17from ding.config import save_config_py, compile_config 18from ding.model import ContinuousQAC 19from ding.data import DequeBuffer 20from ding.bonus.common import TrainingReturn, EvalReturn 21from ding.config.example.DDPG import supported_env_cfg 22from ding.config.example.DDPG import supported_env 23 24 25class DDPGAgent: 26 """ 27 Overview: 28 Class of agent for training, evaluation and deployment of Reinforcement learning algorithm \ 29 Deep Deterministic Policy Gradient(DDPG). 30 For more information about the system design of RL agent, please refer to \ 31 <https://di-engine-docs.readthedocs.io/en/latest/03_system/agent.html>. 32 Interface: 33 ``__init__``, ``train``, ``deploy``, ``collect_data``, ``batch_evaluate``, ``best`` 34 """ 35 supported_env_list = list(supported_env_cfg.keys()) 36 """ 37 Overview: 38 List of supported envs. 39 Examples: 40 >>> from ding.bonus.ddpg import DDPGAgent 41 >>> print(DDPGAgent.supported_env_list) 42 """ 43 44 def __init__( 45 self, 46 env_id: str = None, 47 env: BaseEnv = None, 48 seed: int = 0, 49 exp_name: str = None, 50 model: Optional[torch.nn.Module] = None, 51 cfg: Optional[Union[EasyDict, dict]] = None, 52 policy_state_dict: str = None, 53 ) -> None: 54 """ 55 Overview: 56 Initialize agent for DDPG algorithm. 57 Arguments: 58 - env_id (:obj:`str`): The environment id, which is a registered environment name in gym or gymnasium. \ 59 If ``env_id`` is not specified, ``env_id`` in ``cfg.env`` must be specified. \ 60 If ``env_id`` is specified, ``env_id`` in ``cfg.env`` will be ignored. \ 61 ``env_id`` should be one of the supported envs, which can be found in ``supported_env_list``. 62 - env (:obj:`BaseEnv`): The environment instance for training and evaluation. \ 63 If ``env`` is not specified, `env_id`` or ``cfg.env.env_id`` must be specified. \ 64 ``env_id`` or ``cfg.env.env_id`` will be used to create environment instance. \ 65 If ``env`` is specified, ``env_id`` and ``cfg.env.env_id`` will be ignored. 66 - seed (:obj:`int`): The random seed, which is set before running the program. \ 67 Default to 0. 68 - exp_name (:obj:`str`): The name of this experiment, which will be used to create the folder to save \ 69 log data. Default to None. If not specified, the folder name will be ``env_id``-``algorithm``. 70 - model (:obj:`torch.nn.Module`): The model of DDPG algorithm, which should be an instance of class \ 71 :class:`ding.model.ContinuousQAC`. \ 72 If not specified, a default model will be generated according to the configuration. 73 - cfg (:obj:`Union[EasyDict, dict]`): The configuration of DDPG algorithm, which is a dict. \ 74 Default to None. If not specified, the default configuration will be used. \ 75 The default configuration can be found in ``ding/config/example/DDPG/gym_lunarlander_v2.py``. 76 - policy_state_dict (:obj:`str`): The path of policy state dict saved by PyTorch a in local file. \ 77 If specified, the policy will be loaded from this file. Default to None. 78 79 .. note:: 80 An RL Agent Instance can be initialized in two basic ways. \ 81 For example, we have an environment with id ``LunarLanderContinuous-v2`` registered in gym, \ 82 and we want to train an agent with DDPG algorithm with default configuration. \ 83 Then we can initialize the agent in the following ways: 84 >>> agent = DDPGAgent(env_id='LunarLanderContinuous-v2') 85 or, if we want can specify the env_id in the configuration: 86 >>> cfg = {'env': {'env_id': 'LunarLanderContinuous-v2'}, 'policy': ...... } 87 >>> agent = DDPGAgent(cfg=cfg) 88 There are also other arguments to specify the agent when initializing. 89 For example, if we want to specify the environment instance: 90 >>> env = CustomizedEnv('LunarLanderContinuous-v2') 91 >>> agent = DDPGAgent(cfg=cfg, env=env) 92 or, if we want to specify the model: 93 >>> model = ContinuousQAC(**cfg.policy.model) 94 >>> agent = DDPGAgent(cfg=cfg, model=model) 95 or, if we want to reload the policy from a saved policy state dict: 96 >>> agent = DDPGAgent(cfg=cfg, policy_state_dict='LunarLanderContinuous-v2.pth.tar') 97 Make sure that the configuration is consistent with the saved policy state dict. 98 """ 99 100 assert env_id is not None or cfg is not None, "Please specify env_id or cfg." 101 102 if cfg is not None and not isinstance(cfg, EasyDict): 103 cfg = EasyDict(cfg) 104 105 if env_id is not None: 106 assert env_id in DDPGAgent.supported_env_list, "Please use supported envs: {}".format( 107 DDPGAgent.supported_env_list 108 ) 109 if cfg is None: 110 cfg = supported_env_cfg[env_id] 111 else: 112 assert cfg.env.env_id == env_id, "env_id in cfg should be the same as env_id in args." 113 else: 114 assert hasattr(cfg.env, "env_id"), "Please specify env_id in cfg." 115 assert cfg.env.env_id in DDPGAgent.supported_env_list, "Please use supported envs: {}".format( 116 DDPGAgent.supported_env_list 117 ) 118 default_policy_config = EasyDict({"policy": DDPGPolicy.default_config()}) 119 default_policy_config.update(cfg) 120 cfg = default_policy_config 121 122 if exp_name is not None: 123 cfg.exp_name = exp_name 124 self.cfg = compile_config(cfg, policy=DDPGPolicy) 125 self.exp_name = self.cfg.exp_name 126 if env is None: 127 self.env = supported_env[cfg.env.env_id](cfg=cfg.env) 128 else: 129 assert isinstance(env, BaseEnv), "Please use BaseEnv as env data type." 130 self.env = env 131 132 logging.getLogger().setLevel(logging.INFO) 133 self.seed = seed 134 set_pkg_seed(self.seed, use_cuda=self.cfg.policy.cuda) 135 if not os.path.exists(self.exp_name): 136 os.makedirs(self.exp_name) 137 save_config_py(self.cfg, os.path.join(self.exp_name, 'policy_config.py')) 138 if model is None: 139 model = ContinuousQAC(**self.cfg.policy.model) 140 self.buffer_ = DequeBuffer(size=self.cfg.policy.other.replay_buffer.replay_buffer_size) 141 self.policy = DDPGPolicy(self.cfg.policy, model=model) 142 if policy_state_dict is not None: 143 self.policy.learn_mode.load_state_dict(policy_state_dict) 144 self.checkpoint_save_dir = os.path.join(self.exp_name, "ckpt") 145 146 def train( 147 self, 148 step: int = int(1e7), 149 collector_env_num: int = None, 150 evaluator_env_num: int = None, 151 n_iter_log_show: int = 500, 152 n_iter_save_ckpt: int = 1000, 153 context: Optional[str] = None, 154 debug: bool = False, 155 wandb_sweep: bool = False, 156 ) -> TrainingReturn: 157 """ 158 Overview: 159 Train the agent with DDPG algorithm for ``step`` iterations with ``collector_env_num`` collector \ 160 environments and ``evaluator_env_num`` evaluator environments. Information during training will be \ 161 recorded and saved by wandb. 162 Arguments: 163 - step (:obj:`int`): The total training environment steps of all collector environments. Default to 1e7. 164 - collector_env_num (:obj:`int`): The collector environment number. Default to None. \ 165 If not specified, it will be set according to the configuration. 166 - evaluator_env_num (:obj:`int`): The evaluator environment number. Default to None. \ 167 If not specified, it will be set according to the configuration. 168 - n_iter_save_ckpt (:obj:`int`): The frequency of saving checkpoint every training iteration. \ 169 Default to 1000. 170 - context (:obj:`str`): The multi-process context of the environment manager. Default to None. \ 171 It can be specified as ``spawn``, ``fork`` or ``forkserver``. 172 - debug (:obj:`bool`): Whether to use debug mode in the environment manager. Default to False. \ 173 If set True, base environment manager will be used for easy debugging. Otherwise, \ 174 subprocess environment manager will be used. 175 - wandb_sweep (:obj:`bool`): Whether to use wandb sweep, \ 176 which is a hyper-parameter optimization process for seeking the best configurations. \ 177 Default to False. If True, the wandb sweep id will be used as the experiment name. 178 Returns: 179 - (:obj:`TrainingReturn`): The training result, of which the attributions are: 180 - wandb_url (:obj:`str`): The weight & biases (wandb) project url of the trainning experiment. 181 """ 182 183 if debug: 184 logging.getLogger().setLevel(logging.DEBUG) 185 logging.debug(self.policy._model) 186 # define env and policy 187 collector_env_num = collector_env_num if collector_env_num else self.cfg.env.collector_env_num 188 evaluator_env_num = evaluator_env_num if evaluator_env_num else self.cfg.env.evaluator_env_num 189 collector_env = setup_ding_env_manager(self.env, collector_env_num, context, debug, 'collector') 190 evaluator_env = setup_ding_env_manager(self.env, evaluator_env_num, context, debug, 'evaluator') 191 192 with task.start(ctx=OnlineRLContext()): 193 task.use( 194 interaction_evaluator( 195 self.cfg, 196 self.policy.eval_mode, 197 evaluator_env, 198 render=self.cfg.policy.eval.render if hasattr(self.cfg.policy.eval, "render") else False 199 ) 200 ) 201 task.use(CkptSaver(policy=self.policy, save_dir=self.checkpoint_save_dir, train_freq=n_iter_save_ckpt)) 202 task.use( 203 StepCollector( 204 self.cfg, 205 self.policy.collect_mode, 206 collector_env, 207 random_collect_size=self.cfg.policy.random_collect_size 208 if hasattr(self.cfg.policy, 'random_collect_size') else 0, 209 ) 210 ) 211 task.use(data_pusher(self.cfg, self.buffer_)) 212 task.use(OffPolicyLearner(self.cfg, self.policy.learn_mode, self.buffer_)) 213 task.use( 214 wandb_online_logger( 215 metric_list=self.policy._monitor_vars_learn(), 216 model=self.policy._model, 217 anonymous=True, 218 project_name=self.exp_name, 219 wandb_sweep=wandb_sweep, 220 ) 221 ) 222 task.use(termination_checker(max_env_step=step)) 223 task.use(final_ctx_saver(name=self.exp_name)) 224 task.run() 225 226 return TrainingReturn(wandb_url=task.ctx.wandb_url) 227 228 def deploy( 229 self, 230 enable_save_replay: bool = False, 231 concatenate_all_replay: bool = False, 232 replay_save_path: str = None, 233 seed: Optional[Union[int, List]] = None, 234 debug: bool = False 235 ) -> EvalReturn: 236 """ 237 Overview: 238 Deploy the agent with DDPG algorithm by interacting with the environment, during which the replay video \ 239 can be saved if ``enable_save_replay`` is True. The evaluation result will be returned. 240 Arguments: 241 - enable_save_replay (:obj:`bool`): Whether to save the replay video. Default to False. 242 - concatenate_all_replay (:obj:`bool`): Whether to concatenate all replay videos into one video. \ 243 Default to False. If ``enable_save_replay`` is False, this argument will be ignored. \ 244 If ``enable_save_replay`` is True and ``concatenate_all_replay`` is False, \ 245 the replay video of each episode will be saved separately. 246 - replay_save_path (:obj:`str`): The path to save the replay video. Default to None. \ 247 If not specified, the video will be saved in ``exp_name/videos``. 248 - seed (:obj:`Union[int, List]`): The random seed, which is set before running the program. \ 249 Default to None. If not specified, ``self.seed`` will be used. \ 250 If ``seed`` is an integer, the agent will be deployed once. \ 251 If ``seed`` is a list of integers, the agent will be deployed once for each seed in the list. 252 - debug (:obj:`bool`): Whether to use debug mode in the environment manager. Default to False. \ 253 If set True, base environment manager will be used for easy debugging. Otherwise, \ 254 subprocess environment manager will be used. 255 Returns: 256 - (:obj:`EvalReturn`): The evaluation result, of which the attributions are: 257 - eval_value (:obj:`np.float32`): The mean of evaluation return. 258 - eval_value_std (:obj:`np.float32`): The standard deviation of evaluation return. 259 """ 260 261 if debug: 262 logging.getLogger().setLevel(logging.DEBUG) 263 # define env and policy 264 env = self.env.clone(caller='evaluator') 265 266 if seed is not None and isinstance(seed, int): 267 seeds = [seed] 268 elif seed is not None and isinstance(seed, list): 269 seeds = seed 270 else: 271 seeds = [self.seed] 272 273 returns = [] 274 images = [] 275 if enable_save_replay: 276 replay_save_path = os.path.join(self.exp_name, 'videos') if replay_save_path is None else replay_save_path 277 env.enable_save_replay(replay_path=replay_save_path) 278 else: 279 logging.warning('No video would be generated during the deploy.') 280 if concatenate_all_replay: 281 logging.warning('concatenate_all_replay is set to False because enable_save_replay is False.') 282 concatenate_all_replay = False 283 284 def single_env_forward_wrapper(forward_fn, cuda=True): 285 286 def _forward(obs): 287 # unsqueeze means add batch dim, i.e. (O, ) -> (1, O) 288 obs = ttorch.as_tensor(obs).unsqueeze(0) 289 if cuda and torch.cuda.is_available(): 290 obs = obs.cuda() 291 action = forward_fn(obs, mode='compute_actor')["action"] 292 # squeeze means delete batch dim, i.e. (1, A) -> (A, ) 293 action = action.squeeze(0).detach().cpu().numpy() 294 return action 295 296 return _forward 297 298 forward_fn = single_env_forward_wrapper(self.policy._model, self.cfg.policy.cuda) 299 300 # reset first to make sure the env is in the initial state 301 # env will be reset again in the main loop 302 env.reset() 303 304 for seed in seeds: 305 env.seed(seed, dynamic_seed=False) 306 return_ = 0. 307 step = 0 308 obs = env.reset() 309 images.append(render(env)[None]) if concatenate_all_replay else None 310 while True: 311 action = forward_fn(obs) 312 obs, rew, done, info = env.step(action) 313 images.append(render(env)[None]) if concatenate_all_replay else None 314 return_ += rew 315 step += 1 316 if done: 317 break 318 logging.info(f'DDPG deploy is finished, final episode return with {step} steps is: {return_}') 319 returns.append(return_) 320 321 env.close() 322 323 if concatenate_all_replay: 324 images = np.concatenate(images, axis=0) 325 import imageio 326 imageio.mimwrite(os.path.join(replay_save_path, 'deploy.mp4'), images, fps=get_env_fps(env)) 327 328 return EvalReturn(eval_value=np.mean(returns), eval_value_std=np.std(returns)) 329 330 def collect_data( 331 self, 332 env_num: int = 8, 333 save_data_path: Optional[str] = None, 334 n_sample: Optional[int] = None, 335 n_episode: Optional[int] = None, 336 context: Optional[str] = None, 337 debug: bool = False 338 ) -> None: 339 """ 340 Overview: 341 Collect data with DDPG algorithm for ``n_episode`` episodes with ``env_num`` collector environments. \ 342 The collected data will be saved in ``save_data_path`` if specified, otherwise it will be saved in \ 343 ``exp_name/demo_data``. 344 Arguments: 345 - env_num (:obj:`int`): The number of collector environments. Default to 8. 346 - save_data_path (:obj:`str`): The path to save the collected data. Default to None. \ 347 If not specified, the data will be saved in ``exp_name/demo_data``. 348 - n_sample (:obj:`int`): The number of samples to collect. Default to None. \ 349 If not specified, ``n_episode`` must be specified. 350 - n_episode (:obj:`int`): The number of episodes to collect. Default to None. \ 351 If not specified, ``n_sample`` must be specified. 352 - context (:obj:`str`): The multi-process context of the environment manager. Default to None. \ 353 It can be specified as ``spawn``, ``fork`` or ``forkserver``. 354 - debug (:obj:`bool`): Whether to use debug mode in the environment manager. Default to False. \ 355 If set True, base environment manager will be used for easy debugging. Otherwise, \ 356 subprocess environment manager will be used. 357 """ 358 359 if debug: 360 logging.getLogger().setLevel(logging.DEBUG) 361 if n_episode is not None: 362 raise NotImplementedError 363 # define env and policy 364 env_num = env_num if env_num else self.cfg.env.collector_env_num 365 env = setup_ding_env_manager(self.env, env_num, context, debug, 'collector') 366 367 if save_data_path is None: 368 save_data_path = os.path.join(self.exp_name, 'demo_data') 369 370 # main execution task 371 with task.start(ctx=OnlineRLContext()): 372 task.use( 373 StepCollector( 374 self.cfg, self.policy.collect_mode, env, random_collect_size=self.cfg.policy.random_collect_size 375 ) 376 ) 377 task.use(offline_data_saver(save_data_path, data_type='hdf5')) 378 task.run(max_step=1) 379 logging.info( 380 f'DDPG collecting is finished, more than {n_sample} samples are collected and saved in `{save_data_path}`' 381 ) 382 383 def batch_evaluate( 384 self, 385 env_num: int = 4, 386 n_evaluator_episode: int = 4, 387 context: Optional[str] = None, 388 debug: bool = False 389 ) -> EvalReturn: 390 """ 391 Overview: 392 Evaluate the agent with DDPG algorithm for ``n_evaluator_episode`` episodes with ``env_num`` evaluator \ 393 environments. The evaluation result will be returned. 394 The difference between methods ``batch_evaluate`` and ``deploy`` is that ``batch_evaluate`` will create \ 395 multiple evaluator environments to evaluate the agent to get an average performance, while ``deploy`` \ 396 will only create one evaluator environment to evaluate the agent and save the replay video. 397 Arguments: 398 - env_num (:obj:`int`): The number of evaluator environments. Default to 4. 399 - n_evaluator_episode (:obj:`int`): The number of episodes to evaluate. Default to 4. 400 - context (:obj:`str`): The multi-process context of the environment manager. Default to None. \ 401 It can be specified as ``spawn``, ``fork`` or ``forkserver``. 402 - debug (:obj:`bool`): Whether to use debug mode in the environment manager. Default to False. \ 403 If set True, base environment manager will be used for easy debugging. Otherwise, \ 404 subprocess environment manager will be used. 405 Returns: 406 - (:obj:`EvalReturn`): The evaluation result, of which the attributions are: 407 - eval_value (:obj:`np.float32`): The mean of evaluation return. 408 - eval_value_std (:obj:`np.float32`): The standard deviation of evaluation return. 409 """ 410 411 if debug: 412 logging.getLogger().setLevel(logging.DEBUG) 413 # define env and policy 414 env_num = env_num if env_num else self.cfg.env.evaluator_env_num 415 env = setup_ding_env_manager(self.env, env_num, context, debug, 'evaluator') 416 417 # reset first to make sure the env is in the initial state 418 # env will be reset again in the main loop 419 env.launch() 420 env.reset() 421 422 evaluate_cfg = self.cfg 423 evaluate_cfg.env.n_evaluator_episode = n_evaluator_episode 424 425 # main execution task 426 with task.start(ctx=OnlineRLContext()): 427 task.use(interaction_evaluator(self.cfg, self.policy.eval_mode, env)) 428 task.run(max_step=1) 429 430 return EvalReturn(eval_value=task.ctx.eval_value, eval_value_std=task.ctx.eval_value_std) 431 432 @property 433 def best(self) -> 'DDPGAgent': 434 """ 435 Overview: 436 Load the best model from the checkpoint directory, \ 437 which is by default in folder ``exp_name/ckpt/eval.pth.tar``. \ 438 The return value is the agent with the best model. 439 Returns: 440 - (:obj:`DDPGAgent`): The agent with the best model. 441 Examples: 442 >>> agent = DDPGAgent(env_id='LunarLanderContinuous-v2') 443 >>> agent.train() 444 >>> agent = agent.best 445 446 .. note:: 447 The best model is the model with the highest evaluation return. If this method is called, the current \ 448 model will be replaced by the best model. 449 """ 450 451 best_model_file_path = os.path.join(self.checkpoint_save_dir, "eval.pth.tar") 452 # Load best model if it exists 453 if os.path.exists(best_model_file_path): 454 policy_state_dict = torch.load(best_model_file_path, map_location=torch.device("cpu")) 455 self.policy.learn_mode.load_state_dict(policy_state_dict) 456 return self