# Copyright (c) 2017 Intel Corporation
# 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
# 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.
from typing import List
import numpy as np
from rl_coach.core_types import ActionType
from rl_coach.exploration_policies.exploration_policy import ExplorationParameters, ExplorationPolicy
from rl_coach.spaces import ActionSpace, DiscreteActionSpace, BoxActionSpace
The Greedy exploration policy is intended for both discrete and continuous action spaces.
For discrete action spaces, it always selects the action with the maximum value, as given by the agent.
For continuous action spaces, it always return the exact action, as it was given by the agent.
def __init__(self, action_space: ActionSpace):
:param action_space: the action space used by the environment
def get_action(self, action_values: List[ActionType]):
if type(self.action_space) == DiscreteActionSpace:
action = np.argmax(action_values)
one_hot_action_probabilities = np.zeros(len(self.action_space.actions))
one_hot_action_probabilities[action] = 1
return action, one_hot_action_probabilities
if type(self.action_space) == BoxActionSpace: