Python baselines.common.tf_util.adjust_shape() Examples

The following are 14 code examples of baselines.common.tf_util.adjust_shape(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module baselines.common.tf_util , or try the search function .
Example #1
Source File: ddpg_learner.py    From ICML2019-TREX with MIT License 6 votes vote down vote up 
def step(self, obs, apply_noise=True, compute_Q=True):
        if self.param_noise is not None and apply_noise:
            actor_tf = self.perturbed_actor_tf
        else:
            actor_tf = self.actor_tf
        feed_dict = {self.obs0: U.adjust_shape(self.obs0, [obs])}
        if compute_Q:
            action, q = self.sess.run([actor_tf, self.critic_with_actor_tf], feed_dict=feed_dict)
        else:
            action = self.sess.run(actor_tf, feed_dict=feed_dict)
            q = None

        if self.action_noise is not None and apply_noise:
            noise = self.action_noise()
            assert noise.shape == action[0].shape
            action += noise
        action = np.clip(action, self.action_range[0], self.action_range[1])


        return action, q, None, None
Example #2
Source File: ddpg_learner.py    From StarTrader with MIT License 6 votes vote down vote up 
def step(self, obs, apply_noise=True, compute_Q=True):
        if self.param_noise is not None and apply_noise:
            actor_tf = self.perturbed_actor_tf
        else:
            actor_tf = self.actor_tf
        feed_dict = {self.obs0: U.adjust_shape(self.obs0, [obs])}
        if compute_Q:
            action, q = self.sess.run([actor_tf, self.critic_with_actor_tf], feed_dict=feed_dict)
        else:
            action = self.sess.run(actor_tf, feed_dict=feed_dict)
            q = None

        if self.action_noise is not None and apply_noise:
            noise = self.action_noise()
            assert noise.shape == action[0].shape
            action += noise
        action = np.clip(action, self.action_range[0], self.action_range[1])


        return action, q, None, None
Example #3
Source File: ddpg_learner.py    From baselines with MIT License 6 votes vote down vote up 
def step(self, obs, apply_noise=True, compute_Q=True):
        if self.param_noise is not None and apply_noise:
            actor_tf = self.perturbed_actor_tf
        else:
            actor_tf = self.actor_tf
        feed_dict = {self.obs0: U.adjust_shape(self.obs0, [obs])}
        if compute_Q:
            action, q = self.sess.run([actor_tf, self.critic_with_actor_tf], feed_dict=feed_dict)
        else:
            action = self.sess.run(actor_tf, feed_dict=feed_dict)
            q = None

        if self.action_noise is not None and apply_noise:
            noise = self.action_noise()
            assert noise.shape == action[0].shape
            action += noise
        action = np.clip(action, self.action_range[0], self.action_range[1])


        return action, q, None, None
Example #4
Source File: utils.py    From HardRLWithYoutube with MIT License 5 votes vote down vote up 
def make_feed_dict(self, data):
        return {self._placeholder: adjust_shape(self._placeholder, data)}
Example #5
Source File: policies.py    From HardRLWithYoutube with MIT License 5 votes vote down vote up 
def _evaluate(self, variables, observation, **extra_feed):
        sess = self.sess or tf.get_default_session()
        feed_dict = {self.X: adjust_shape(self.X, observation)}
        for inpt_name, data in extra_feed.items():
            if inpt_name in self.__dict__.keys():
                inpt = self.__dict__[inpt_name]
                if isinstance(inpt, tf.Tensor) and inpt._op.type == 'Placeholder':
                    feed_dict[inpt] = adjust_shape(inpt, data)

        return sess.run(variables, feed_dict)
Example #6
Source File: policies.py    From Reinforcement_Learning_for_Traffic_Light_Control with Apache License 2.0 5 votes vote down vote up 
def _evaluate(self, variables, observation, **extra_feed):
        sess = self.sess
        feed_dict = {self.X: adjust_shape(self.X, observation)}
        for inpt_name, data in extra_feed.items():
            if inpt_name in self.__dict__.keys():
                inpt = self.__dict__[inpt_name]
                if isinstance(inpt, tf.Tensor) and inpt._op.type == 'Placeholder':
                    feed_dict[inpt] = adjust_shape(inpt, data)

        return sess.run(variables, feed_dict)
Example #7
Source File: policies.py    From Reinforcement_Learning_for_Traffic_Light_Control with Apache License 2.0 5 votes vote down vote up 
def _evaluate(self, variables, observation, **extra_feed):
        sess = self.sess
        feed_dict = {self.X: adjust_shape(self.X, observation)}
        for inpt_name, data in extra_feed.items():
            if inpt_name in self.__dict__.keys():
                inpt = self.__dict__[inpt_name]
                if isinstance(inpt, tf.Tensor) and inpt._op.type == 'Placeholder':
                    feed_dict[inpt] = adjust_shape(inpt, data)

        return sess.run(variables, feed_dict)
Example #8
Source File: policies.py    From Reinforcement_Learning_for_Traffic_Light_Control with Apache License 2.0 5 votes vote down vote up 
def _evaluate(self, variables, observation, **extra_feed):
        sess = self.sess
        feed_dict = {self.X: adjust_shape(self.X, observation)}
        for inpt_name, data in extra_feed.items():
            if inpt_name in self.__dict__.keys():
                inpt = self.__dict__[inpt_name]
                if isinstance(inpt, tf.Tensor) and inpt._op.type == 'Placeholder':
                    feed_dict[inpt] = adjust_shape(inpt, data)

        return sess.run(variables, feed_dict)
Example #9
Source File: utils.py    From ICML2019-TREX with MIT License 5 votes vote down vote up 
def make_feed_dict(self, data):
        return {self._placeholder: adjust_shape(self._placeholder, data)}
Example #10
Source File: policies.py    From ICML2019-TREX with MIT License 5 votes vote down vote up 
def _evaluate(self, variables, observation, **extra_feed):
        sess = self.sess
        feed_dict = {self.X: adjust_shape(self.X, observation)}
        for inpt_name, data in extra_feed.items():
            if inpt_name in self.__dict__.keys():
                inpt = self.__dict__[inpt_name]
                if isinstance(inpt, tf.Tensor) and inpt._op.type == 'Placeholder':
                    feed_dict[inpt] = adjust_shape(inpt, data)

        return sess.run(variables, feed_dict)
Example #11
Source File: utils.py    From ICML2019-TREX with MIT License 5 votes vote down vote up 
def make_feed_dict(self, data):
        return {self._placeholder: adjust_shape(self._placeholder, data)}
Example #12
Source File: policies.py    From ICML2019-TREX with MIT License 5 votes vote down vote up 
def _evaluate(self, variables, observation, **extra_feed):
        sess = self.sess
        feed_dict = {self.X: adjust_shape(self.X, observation)}
        for inpt_name, data in extra_feed.items():
            if inpt_name in self.__dict__.keys():
                inpt = self.__dict__[inpt_name]
                if isinstance(inpt, tf.Tensor) and inpt._op.type == 'Placeholder':
                    feed_dict[inpt] = adjust_shape(inpt, data)

        return sess.run(variables, feed_dict)
Example #13
Source File: utils.py    From baselines with MIT License 5 votes vote down vote up 
def make_feed_dict(self, data):
        return {self._placeholder: adjust_shape(self._placeholder, data)}
Example #14
Source File: policies.py    From baselines with MIT License 5 votes vote down vote up 
def _evaluate(self, variables, observation, **extra_feed):
        sess = self.sess
        feed_dict = {self.X: adjust_shape(self.X, observation)}
        for inpt_name, data in extra_feed.items():
            if inpt_name in self.__dict__.keys():
                inpt = self.__dict__[inpt_name]
                if isinstance(inpt, tf.Tensor) and inpt._op.type == 'Placeholder':
                    feed_dict[inpt] = adjust_shape(inpt, data)

        return sess.run(variables, feed_dict)