def test_rewards2(self):
numStates = 5000
numActions = 20
mu = [10, 10, 10]
sigma = [1, 1, 1]
R = np.asarray([[ 1.0, -0.7, -0.5],
[-0.7, 1.0, 0.8],
[-0.5, 0.8, 1.0]])
cov = rewards.cor2cov(R, sigma)
D = rewards.mvnrewards(numStates, numActions, mu, cov)
self.checkCorrelations(R, D)
def test_rewards1(self):
numStates = 1000
numActions = 5
mu = [20, 0, 50]
sigma = [5, 5, 10]
R = np.asarray([[ 1.0, 0.4, -0.4],
[ 0.4, 1.0, 0.6],
[-0.4, 0.6, 1.0]])
cov = rewards.cor2cov(R, sigma)
D = rewards.mvnrewards(numStates, numActions, mu, cov)
self.checkCorrelations(R, D)
def test_rewards3(self):
numStates = 200
numActions = 8
mu = [0, -10, 30, 0]
sigma = [5, 0.5, 10, 2.0]
R = np.asarray([[ 1.0, 0.2, -0.5, 0.0],
[ 0.2, 1.0, 0.4, 0.0],
[-0.5, 0.4, 1.0, 0.6],
[ 0.0, 0.0, 0.6, 1.0]])
cov = rewards.cor2cov(R, sigma)
D = rewards.mvnrewards(numStates, numActions, mu, cov)
self.checkCorrelations(R, D)
params = {'frond_probability': args.frond_probability,
'frond_size': args.frond_size,
'frond_actions': args.frond_actions}
if args.graph_type == 'lobster':
args.actions = 3
transition_graph = grp.create_graph(args.graph_type, args.states, args.actions, params)
# some of the graph types might add nodes and edges, so we should recalculate the
# graph size before continuing
args.states = transition_graph.number_of_nodes()
args.actions = max(transition_graph.out_degree().values())
# create the reward structures
rewards = rwd.mvnrewards(args.states, args.actions, args.rmeans, cov)
io.write_instance(transition_graph, rewards)
print('# type={}, states={}, actions={}, correlation={}, stdev={}'.
format(args.type, args.states, args.actions, args.correlation.tolist(), args.stdev.tolist()))
# calculate some summary statistics on the instance
rewards_est = rwd.correlation(rewards)
print('\n# Summary Statistics')
print('# actual R={}'.format(rewards_est.tolist()))
values.annotate_discrete_graph(transition_graph)
if args.transitions_dot:
#io.output_dot(transition_graph, args.transitions_dot)
with open(args.transitions_dot, 'w') as f:
nx.write_dot(transition_graph, f)
