SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1808.09442 · 2018

Discriminative Deep Dyna-Q: Robust Planning for Dialogue Policy Learning

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 4 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
MiuLab/D3Q canonical 1 of 1
Yuqing2018/D3Q_Python3 pwc_unofficial 0 of 3
FunctionStatusWhere it lives
text_to_dict Ran MiuLab/D3Q/D3Q/src/deep_dialog/dialog_system/dict_reader.py
code served (permissive licence) · get_code("5e4fd7cf91f440fc")
draw Not yet run Yuqing2018/D3Q_Python3/D3Q/src/draw_figure.py
code served (permissive licence) · get_code("a97a8e0856ccb2bc")
read_performance Not yet run Yuqing2018/D3Q_Python3/D3Q/src/draw_figure.py
code served (permissive licence) · get_code("49f5c7b0ffd86759")
show_model_performance Not yet run Yuqing2018/D3Q_Python3/D3Q/src/draw_figure.py
code served (permissive licence) · get_code("8a8a9a5bf7ce2f6d")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

This paper presents a Discriminative Deep Dyna-Q (D3Q) approach to improving the effectiveness and robustness of Deep Dyna-Q (DDQ), a recently proposed framework that extends the Dyna-Q algorithm to integrate planning for task-completion dialogue policy learning. To obviate DDQ's high dependency on the quality of simulated experiences, we incorporate an RNN-based discriminator in D3Q to differentiate simulated experience from real user experience in order to control the quality of training data. Experiments show that D3Q significantly outperforms DDQ by controlling the quality of simulated experience used for planning. The effectiveness and robustness of D3Q is further demonstrated in a domain extension setting, where the agent's capability of adapting to a changing environment is tested.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1808.09442")
get_code_for_paper("1808.09442")
have("1808.09442")

Connect an agent — have() is free.