mirror of
https://github.com/gryf/coach.git
synced 2025-12-17 19:20:19 +01:00
125c7ee38d
Main changes are detailed below: New features - * CARLA 0.7 simulator integration * Human control of the game play * Recording of human game play and storing / loading the replay buffer * Behavioral cloning agent and presets * Golden tests for several presets * Selecting between deep / shallow image embedders * Rendering through pygame (with some boost in performance) API changes - * Improved environment wrapper API * Added an evaluate flag to allow convenient evaluation of existing checkpoints * Improve frameskip definition in Gym Bug fixes - * Fixed loading of checkpoints for agents with more than one network * Fixed the N Step Q learning agent python3 compatibility
41 lines
1.4 KiB
Python
41 lines
1.4 KiB
Python
#
|
|
# 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
|
|
#
|
|
# 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.
|
|
#
|
|
|
|
from agents.imitation_agent import *
|
|
|
|
|
|
# Behavioral Cloning Agent
|
|
class BCAgent(ImitationAgent):
|
|
def __init__(self, env, tuning_parameters, replicated_device=None, thread_id=0):
|
|
ImitationAgent.__init__(self, env, tuning_parameters, replicated_device, thread_id)
|
|
|
|
def learn_from_batch(self, batch):
|
|
current_states, _, actions, _, _, _ = self.extract_batch(batch)
|
|
|
|
# create the inputs for the network
|
|
input = current_states
|
|
|
|
# the targets for the network are the actions since this is supervised learning
|
|
if self.env.discrete_controls:
|
|
targets = np.eye(self.env.action_space_size)[[actions]]
|
|
else:
|
|
targets = actions
|
|
|
|
result = self.main_network.train_and_sync_networks(input, targets)
|
|
total_loss = result[0]
|
|
|
|
return total_loss
|