def action_bits(self):
""" Returns the maximum number of bits required to represent an action.
"""
actions = [util.bits_required(action) for action in self.valid_actions]
return max(actions)
def observation_bits(self):
""" Returns the maximum number of bits required to represent an observation.
"""
observations = [
util.bits_required(obs) for obs in self.valid_observations
]
return max(observations)
def action_bits(self):
""" Returns the maximum number of bits required to represent an action.
"""
# TODO（DONE）: implement
bits_list = []
# Check the number of bits required to represent every action
for action in self.valid_actions:
bits_list.append(util.bits_required(action))
# Return the max number of bits required
return max(bits_list)
def reward_bits(self):
""" Returns the maximum number of bits required to represent a reward.
"""
# TODO（DONE）: implement
bits_list = []
# Check the number of bits required to represent every reward
for reward in self.valid_rewards:
bits_list.append(util.bits_required(reward))
# Return the max number of bits required
return max(bits_list)
def action_bits(self):
""" Returns the maximum number of bits required to represent an action.
(Called `actionBits` in the C++ version.)
"""
# Find the largest sized observation.
maximum_bits = 0
for action in self.valid_actions:
bits_for_this_action = util.bits_required(action)
if bits_for_this_action > maximum_bits:
maximum_bits = bits_for_this_action
# end if
# end for
return maximum_bits
def reward_bits(self):
""" Returns the maximum number of bits required to represent a reward.
(Called `rewardBits` in the C++ version)
"""
# Find the largest sized reward.
maximum_bits = 0
for reward in self.valid_rewards:
bits_for_this_reward = util.bits_required(reward)
if bits_for_this_reward > maximum_bits:
maximum_bits = bits_for_this_reward
# end if
# end for
return maximum_bits
def action_bits(self):
""" Returns the maximum number of bits required to represent an action.
(Called `actionBits` in the C++ version.)
"""
# Find the largest sized observation.
maximum_bits = 0
for action in self.valid_actions:
bits_for_this_action = util.bits_required(action)
if bits_for_this_action > maximum_bits:
maximum_bits = bits_for_this_action
# end if
# end for
return maximum_bits
def reward_bits(self):
""" Returns the maximum number of bits required to represent a reward.
(Called `rewardBits` in the C++ version)
"""
# Find the largest sized reward.
maximum_bits = 0
for reward in self.valid_rewards:
bits_for_this_reward = util.bits_required(reward)
if bits_for_this_reward > maximum_bits:
maximum_bits = bits_for_this_reward
# end if
# end for
return maximum_bits
def reward_bits(self):
""" Returns the maximum number of bits required to represent a reward.
"""
return util.bits_required(self.reward)
#!/usr/bin/env python3 # -*- coding: utf-8 -*- """ Created on Sun Sep 22 17:05:54 2019 @author: andrewtanggara """ from pyaixi import agent, prediction, search, util from pyaixi.environment import Environment b = util.bits_required(7) print(b)