Unity 机器学习代理工具包 (ML-Agents) 是一个开源项目,它使游戏和模拟能够作为训练智能代理的环境。
您最多选择25个主题 主题必须以中文或者字母或数字开头,可以包含连字符 (-),并且长度不得超过35个字符
 
 
 
 
 

32 行
1.4 KiB

import numpy as np
from mlagents.trainers.buffer import AgentBuffer
from mlagents_envs.base_env import BehaviorSpec
from mlagents.trainers.trajectory import SplitObservations
def create_agent_buffer(
behavior_spec: BehaviorSpec, number: int, reward: float = 0.0
) -> AgentBuffer:
buffer = AgentBuffer()
curr_observations = [
np.random.normal(size=shape) for shape in behavior_spec.observation_shapes
]
next_observations = [
np.random.normal(size=shape) for shape in behavior_spec.observation_shapes
]
action = behavior_spec.create_random_action(1)[0, :]
for _ in range(number):
curr_split_obs = SplitObservations.from_observations(curr_observations)
next_split_obs = SplitObservations.from_observations(next_observations)
for i, _ in enumerate(curr_split_obs.visual_observations):
buffer["visual_obs%d" % i].append(curr_split_obs.visual_observations[i])
buffer["next_visual_obs%d" % i].append(
next_split_obs.visual_observations[i]
)
buffer["vector_obs"].append(curr_split_obs.vector_observations)
buffer["next_vector_in"].append(next_split_obs.vector_observations)
buffer["actions"].append(action)
buffer["reward"].append(np.ones(1, dtype=np.float32) * reward)
buffer["masks"].append(np.ones(1, dtype=np.float32))
buffer["done"] = np.zeros(number, dtype=np.float32)
return buffer