minihack/agent/polybeast/models/base.py [337:410]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
                nn.ReLU(),
                # conv5
                nn.Conv1d(self.msg_hdim, self.msg_hdim, kernel_size=3),
                nn.ReLU(),
                # conv6
                nn.Conv1d(self.msg_hdim, self.msg_hdim, kernel_size=3),
                nn.ReLU(),
                nn.MaxPool1d(kernel_size=3, stride=3),
                # fc receives -- [ B x h_dim x 5 ]
                Flatten(),
                nn.Linear(5 * self.msg_hdim, 2 * self.msg_hdim),
                nn.ReLU(),
                nn.Linear(2 * self.msg_hdim, self.msg_hdim),
            )  # final output -- [ B x h_dim x 5 ]
        elif self.msg_model in ("gru", "lstm"):

            def rnn(flag):
                return nn.LSTM if flag == "lstm" else nn.GRU

            self.char_rnn = rnn(self.msg_model)(
                self.msg_edim,
                self.msg_hdim // 2,
                batch_first=True,
                bidirectional=True,
            )
        elif self.msg_model != "none":
            raise NotImplementedError("msg.model == %s", flags.msg.model)

        self.embed_features = nn.Sequential(
            nn.Linear(self.num_features, self.k_dim),
            nn.ReLU(),
            nn.Linear(self.k_dim, self.k_dim),
            nn.ReLU(),
        )

        self.equalize_input_dim = flags.equalize_input_dim
        if not self.equalize_input_dim:
            # just added up the output dimensions of the input featurizers
            # feature / status dim
            out_dim = self.k_dim
            # CNN over full glyph map
            out_dim += self.H * self.W * self.Y
            if self.crop_model == "transformer":
                out_dim += self.crop_dim ** 2 * K
            elif self.crop_model == "cnn":
                out_dim += self.crop_dim ** 2 * self.Y
            # messaging model
            if self.msg_model != "none":
                out_dim += self.msg_hdim
        else:
            # otherwise, project them all to h_dim
            NUM_INPUTS = 4 if self.msg_model != "none" else 3
            project_hdim = flags.equalize_factor * self.h_dim
            out_dim = project_hdim * NUM_INPUTS

            # set up linear layers for projections
            self.project_feature_dim = nn.Linear(self.k_dim, project_hdim)
            self.project_glyph_dim = nn.Linear(
                self.H * self.W * self.Y, project_hdim
            )
            c__2 = self.crop_dim ** 2
            if self.crop_model == "transformer":
                self.project_crop_dim = nn.Linear(c__2 * K, project_hdim)
            elif self.crop_model == "cnn":
                self.project_crop_dim = nn.Linear(c__2 * self.Y, project_hdim)
            if self.msg_model != "none":
                self.project_msg_dim = nn.Linear(self.msg_hdim, project_hdim)

        self.fc = nn.Sequential(
            nn.Linear(out_dim, self.h_dim),
            nn.ReLU(),
            nn.Linear(self.h_dim, self.h_dim),
            nn.ReLU(),
        )
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



minihack/agent/rllib/models.py [331:404]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
                nn.ReLU(),
                # conv5
                nn.Conv1d(self.msg_hdim, self.msg_hdim, kernel_size=3),
                nn.ReLU(),
                # conv6
                nn.Conv1d(self.msg_hdim, self.msg_hdim, kernel_size=3),
                nn.ReLU(),
                nn.MaxPool1d(kernel_size=3, stride=3),
                # fc receives -- [ B x h_dim x 5 ]
                Flatten(),
                nn.Linear(5 * self.msg_hdim, 2 * self.msg_hdim),
                nn.ReLU(),
                nn.Linear(2 * self.msg_hdim, self.msg_hdim),
            )  # final output -- [ B x h_dim x 5 ]
        elif self.msg_model in ("gru", "lstm"):

            def rnn(flag):
                return nn.LSTM if flag == "lstm" else nn.GRU

            self.char_rnn = rnn(self.msg_model)(
                self.msg_edim,
                self.msg_hdim // 2,
                batch_first=True,
                bidirectional=True,
            )
        elif self.msg_model != "none":
            raise NotImplementedError("msg.model == %s", flags.msg.model)

        self.embed_features = nn.Sequential(
            nn.Linear(self.num_features, self.k_dim),
            nn.ReLU(),
            nn.Linear(self.k_dim, self.k_dim),
            nn.ReLU(),
        )

        self.equalize_input_dim = flags.equalize_input_dim
        if not self.equalize_input_dim:
            # just added up the output dimensions of the input featurizers
            # feature / status dim
            out_dim = self.k_dim
            # CNN over full glyph map
            out_dim += self.H * self.W * self.Y
            if self.crop_model == "transformer":
                out_dim += self.crop_dim ** 2 * K
            elif self.crop_model == "cnn":
                out_dim += self.crop_dim ** 2 * self.Y
            # messaging model
            if self.msg_model != "none":
                out_dim += self.msg_hdim
        else:
            # otherwise, project them all to h_dim
            NUM_INPUTS = 4 if self.msg_model != "none" else 3
            project_hdim = flags.equalize_factor * self.h_dim
            out_dim = project_hdim * NUM_INPUTS

            # set up linear layers for projections
            self.project_feature_dim = nn.Linear(self.k_dim, project_hdim)
            self.project_glyph_dim = nn.Linear(
                self.H * self.W * self.Y, project_hdim
            )
            c__2 = self.crop_dim ** 2
            if self.crop_model == "transformer":
                self.project_crop_dim = nn.Linear(c__2 * K, project_hdim)
            elif self.crop_model == "cnn":
                self.project_crop_dim = nn.Linear(c__2 * self.Y, project_hdim)
            if self.msg_model != "none":
                self.project_msg_dim = nn.Linear(self.msg_hdim, project_hdim)

        self.fc = nn.Sequential(
            nn.Linear(out_dim, self.h_dim),
            nn.ReLU(),
            nn.Linear(self.h_dim, self.h_dim),
            nn.ReLU(),
        )
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -