2

为 DDPG 使用离线体验时出错。自定义环境维度（动作空间和状态空间）似乎与 DDPG RLLIB 培训师的预期不一致。

Ubuntu，Ray 0.7 版本（最新的 ray），DDPG 示例，离线数据集。用于离线数据集的采样器构建器。

用这个经验数据估计的 DQN 并运行通过。将环境动作空间更改为连续 (Box(,1)) 并且 DDPG 不起作用。

from ray.tune.registry import register_env

TRAIN_BATCH_SIZE = 512
class mmt_ctns_offline_logs(gym.Env):
    def __init__(self):
        self.action_space = Box(0,50,shape=(,1), dtype=np.float32) #one dimension action space, values range 0 to 50 max
        self.observation_space = Box(-100000, 100000, shape=(,58), dtype=np.float32) #58 columns in state space

register_env("mmt_env_ctnaction", lambda config: mmt_ctns_offline_logs()) #register custom environment 

#define the configuration. Some of these are defaults. But I have explicitely defined them for clarify (within my team)
config_dict = {"env": "mmt_env_ctnaction", "evaluation_num_episodes":50, "num_workers": 11, "sample_batch_size": 512, 
               "train_batch_size": TRAIN_BATCH_SIZE, 
               "input": "<experience_replay_folder>/", 
               "output": "<any_folder>", "gamma": 0.99, 
               "horizon": None,  
               "optimizer_class": "SyncReplayOptimizer", 
               "optimizer": {"prioritized_replay":True},
               "actor_hiddens": [128, 64], "actor_hidden_activation": "relu",
               "critic_hiddens": [64, 64], "critic_hidden_activation": "relu", "n_step": 1,
               "target_network_update_freq": 500,
               "input_evaluation": [], 
               "ignore_worker_failures":True, 'log_level': "DEBUG",
    "buffer_size": 50000,
    "prioritized_replay": True,
    "prioritized_replay_alpha": 0.6,
    "prioritized_replay_beta": 0.4,
    "prioritized_replay_eps": 1e-6,
    "compress_observations": False,
    "lr": 1e-3,
    "actor_loss_coeff": 0.1,
    "critic_loss_coeff": 1.0,
    "use_huber": False,
    "huber_threshold": 1.0,
    "l2_reg": 1e-6,
    "grad_norm_clipping": True,
    "learning_starts": 1500,
    }

config = ddpg.DEFAULT_CONFIG.copy() #dqn.DEFAULT_CONFIG.copy()
for k,v in config_dict.items():
    config[k] = v
config_ddpg = config
config_ddpg

run_experiments({
  'NM_testing_DDPG_offpolicy_noIS': {
    'run': 'DDPG',
    'env': 'mmt_env_ctnaction',
    'config': config_ddpg,
    'local_dir': "/oxygen/narasimham/ray/tmp/mmt/mmt_user_27_DDPG/" 
  },
})

DDPG 迭代的预期结果。

实际 - 错误：-

ray.exceptions.RayTaskError: ray_DDPGTrainer:train() (pid=89635, host=ip-10-114-53-179)
  File "/home/ubuntu/anaconda3/envs/tf_p36n/lib/python3.6/site-packages/ray/rllib/utils/tf_run_builder.py", line 49, in get
    self.feed_dict, os.environ.get("TF_TIMELINE_DIR"))
  File "/home/ubuntu/anaconda3/envs/tf_p36n/lib/python3.6/site-packages/ray/rllib/utils/tf_run_builder.py", line 91, in run_timeline
    fetches = sess.run(ops, feed_dict=feed_dict)
  File "/home/ubuntu/anaconda3/envs/tf_p36n/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 877, in run
    run_metadata_ptr)
  File "/home/ubuntu/anaconda3/envs/tf_p36n/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1076, in _run
    str(subfeed_t.get_shape())))
ValueError: Cannot feed value of shape (512,) for Tensor 'default_policy/action:0', which has shape '(?, 1)'

During handling of the above exception, another exception occurred:
4

1 回答 1

1

尝试如下操作空间定义：

self.action_space = Box(0,50,shape=(1,), dtype=np.float32)
于 2019-11-19T04:35:24.220 回答