def __init__(self, env, results_path, tok, episode_len=20):
super(Seq2SeqAgent, self).__init__(env, results_path)
self.tok = tok
self.episode_len = episode_len
self.feature_size = self.env.feature_size
# Models
enc_hidden_size = args.rnn_dim//2 if args.bidir else args.rnn_dim
self.encoder = model.EncoderLSTM(tok.vocab_size(), args.wemb, enc_hidden_size, padding_idx,
args.dropout, bidirectional=args.bidir).cuda()
self.decoder = model.AttnDecoderLSTM(args.aemb, args.rnn_dim, args.dropout, feature_size=self.feature_size + args.angle_feat_size).cuda()
self.critic = model.Critic().cuda()
self.models = (self.encoder, self.decoder, self.critic)
# Optimizers
self.encoder_optimizer = args.optimizer(self.encoder.parameters(), lr=args.lr)
self.decoder_optimizer = args.optimizer(self.decoder.parameters(), lr=args.lr)
self.critic_optimizer = args.optimizer(self.critic.parameters(), lr=args.lr)
self.optimizers = (self.encoder_optimizer, self.decoder_optimizer, self.critic_optimizer)
# Evaluations
self.losses = []
self.criterion = nn.CrossEntropyLoss(ignore_index=args.ignoreid, size_average=False)
# Logs
sys.stdout.flush()
self.logs = defaultdict(list)
def __init__(self, env, results_path, tok, episode_len=20):
super(Seq2PolicyAgent, self).__init__(env, results_path)
self._iter = 0
self.tok = tok
self.episode_len = episode_len
self.feature_size = self.env.feature_size
# Models
enc_hidden_size = args.rnn_dim//2 if args.bidir else args.rnn_dim
self.encoder = model.EncoderLSTM(tok.vocab_size(), args.wemb, enc_hidden_size, padding_idx,
args.dropout, bidirectional=args.bidir).cuda()
if args.original_decoder:
self.decoder = model.AttnDecoderLSTM(args.aemb, args.rnn_dim, args.dropout, feature_size=self.feature_size + args.angle_feat_size).cuda()
else:
self.decoder = model.AttnPolicyLSTM(args.aemb, args.rnn_dim, args.dropout, feature_size=self.feature_size + args.angle_feat_size, latent_dim=args.vae_latent_dim).cuda()
if args.fix_vae:
print("fix the parameters in sub policy")
for param in self.decoder.policy.parameters():
param.requires_grad = False
self.critic = model.Critic().cuda()
self.models = (self.encoder, self.decoder, self.critic)
# Optimizers
self.encoder_optimizer = args.optimizer(self.encoder.parameters(), lr=args.lr)
self.decoder_optimizer = args.optimizer(self.decoder.parameters(), lr=args.lr)
self.critic_optimizer = args.optimizer(self.critic.parameters(), lr=args.lr)
self.optimizers = (self.encoder_optimizer, self.decoder_optimizer, self.critic_optimizer)
# Evaluations
self.losses = []
self.criterion = nn.CrossEntropyLoss(ignore_index=args.ignoreid, size_average=False)
# Logs
sys.stdout.flush()
self.logs = defaultdict(list)