log_dir=os.path.join(args.log, 'movie'),
record_video=args.record)
env.env.seed(args.seed)
if args.c2d:
env = C2DEnv(env)
observation_space = env.observation_space
action_space = env.action_space
if args.rnn:
pol_net = PolNetLSTM(observation_space,
action_space,
h_size=256,
cell_size=256)
else:
pol_net = PolNet(observation_space, action_space)
if isinstance(action_space, gym.spaces.Box):
pol = GaussianPol(observation_space,
action_space,
pol_net,
args.rnn,
data_parallel=args.data_parallel,
parallel_dim=1 if args.rnn else 0)
elif isinstance(action_space, gym.spaces.Discrete):
pol = CategoricalPol(observation_space,
action_space,
pol_net,
args.rnn,
data_parallel=args.data_parallel,
parallel_dim=1 if args.rnn else 0)
elif isinstance(action_space, gym.spaces.MultiDiscrete):
set_device(device)
score_file = os.path.join(args.log, 'progress.csv')
logger.add_tabular_output(score_file)
env = GymEnv(args.env_name,
log_dir=os.path.join(args.log, 'movie'),
record_video=args.record)
env.env.seed(args.seed)
if args.c2d:
env = C2DEnv(env)
observation_space = env.observation_space
action_space = env.action_space
pol_net = PolNet(observation_space, action_space)
if isinstance(action_space, gym.spaces.Box):
pol = GaussianPol(observation_space,
action_space,
pol_net,
data_parallel=args.data_parallel)
elif isinstance(action_space, gym.spaces.Discrete):
pol = CategoricalPol(observation_space,
action_space,
pol_net,
data_parallel=args.data_parallel)
elif isinstance(action_space, gym.spaces.MultiDiscrete):
pol = MultiCategoricalPol(observation_space,
action_space,
pol_net,
data_parallel=args.data_parallel)
device_name = 'cpu' if args.cuda < 0 else "cuda:{}".format(args.cuda)
device = torch.device(device_name)
set_device(device)
score_file = os.path.join(args.log, 'progress.csv')
logger.add_tabular_output(score_file)
env = GymEnv(args.env_name, log_dir=os.path.join(
args.log, 'movie'), record_video=args.record)
env.env.seed(args.seed)
observation_space = env.observation_space
action_space = env.action_space
pol_net = PolNet(observation_space, action_space)
pol = GaussianPol(observation_space, action_space, pol_net)
targ_pol_net = PolNet(observation_space, action_space)
targ_pol_net.load_state_dict(pol_net.state_dict())
targ_pol = GaussianPol(observation_space, action_space, targ_pol_net)
qf_net = QNet(observation_space, action_space)
qf = DeterministicSAVfunc(observation_space, action_space, qf_net)
targ_qf_net = QNet(observation_space, action_space)
targ_qf_net.load_state_dict(targ_qf_net.state_dict())
targ_qf = DeterministicSAVfunc(observation_space, action_space, targ_qf_net)
sampler = EpiSampler(env, pol, args.num_parallel, seed=args.seed)