|
- # Copyright (c) 2018 PaddlePaddle Authors. All Rights Reserved.
- #
- # Licensed under the Apache License, Version 2.0 (the "License");
- # you may not use this file except in compliance with the License.
- # You may obtain a copy of the License at
- #
- # http://www.apache.org/licenses/LICENSE-2.0
- #
- # Unless required by applicable law or agreed to in writing, software
- # distributed under the License is distributed on an "AS IS" BASIS,
- # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- # See the License for the specific language governing permissions and
- # limitations under the License.
-
- import numpy as np
- import paddle.fluid as fluid
- import parl
- from parl import layers
-
-
- class CartpoleAgent(parl.Agent):
- def __init__(self, algorithm, obs_dim, act_dim):
- self.obs_dim = obs_dim
- self.act_dim = act_dim
- super(CartpoleAgent, self).__init__(algorithm)
-
- def build_program(self):
- self.pred_program = fluid.Program()
- self.learn_program = fluid.Program()
-
- with fluid.program_guard(self.pred_program):
- obs = layers.data(
- name='obs', shape=[self.obs_dim], dtype='float32')
- self.act_prob = self.alg.predict(obs)
-
- with fluid.program_guard(self.learn_program):
- obs = layers.data(
- name='obs', shape=[self.obs_dim], dtype='float32')
- act = layers.data(name='act', shape=[1], dtype='int64')
- reward = layers.data(name='reward', shape=[], dtype='float32')
- self.cost = self.alg.learn(obs, act, reward)
-
- def sample(self, obs):
- obs = np.expand_dims(obs, axis=0)
- act_prob = self.fluid_executor.run(
- self.pred_program,
- feed={'obs': obs.astype('float32')},
- fetch_list=[self.act_prob])[0]
- act_prob = np.squeeze(act_prob, axis=0)
- act = np.random.choice(range(self.act_dim), p=act_prob)
- return act
-
- def predict(self, obs):
- obs = np.expand_dims(obs, axis=0)
- act_prob = self.fluid_executor.run(
- self.pred_program,
- feed={'obs': obs.astype('float32')},
- fetch_list=[self.act_prob])[0]
- act_prob = np.squeeze(act_prob, axis=0)
- act = np.argmax(act_prob)
- return act
-
- def learn(self, obs, act, reward):
- act = np.expand_dims(act, axis=-1)
- feed = {
- 'obs': obs.astype('float32'),
- 'act': act.astype('int64'),
- 'reward': reward.astype('float32')
- }
- cost = self.fluid_executor.run(
- self.learn_program, feed=feed, fetch_list=[self.cost])[0]
- return cost
|