scholarly journals Enhancing Dialog Coherence with Event Graph Grounded Content Planning

2020 ◽  
Author(s):  
Jun Xu ◽  
Zeyang Lei ◽  
Haifeng Wang ◽  
Zheng-Yu Niu ◽  
Hua Wu ◽  
...  
Keyword(s):  
Decision Making ◽  
Reinforcement Learning ◽  
Policy Decision ◽  
Experimental Results ◽  
Open Domain ◽  
Narrative Texts ◽  
Policy Decision Making ◽  
Event Planning ◽  
High Level ◽  
Event Chains

How to generate informative, coherent and sustainable open-domain conversations is a non-trivial task. Previous work on knowledge grounded conversation generation focus on improving dialog informativeness with little attention on dialog coherence. In this paper, to enhance multi-turn dialog coherence, we propose to leverage event chains to help determine a sketch of a multi-turn dialog. We first extract event chains from narrative texts and connect them as a graph. We then present a novel event graph grounded Reinforcement Learning (RL) framework. It conducts high-level response content (simply an event) planning by learning to walk over the graph, and then produces a response conditioned on the planned content. In particular, we devise a novel multi-policy decision making mechanism to foster a coherent dialog with both appropriate content ordering and high contextual relevance. Experimental results indicate the effectiveness of this framework in terms of dialog coherence and informativeness.

Small Group Effects on Foreign Policy Decision Making

2017 ◽  
Author(s):  
Jean A. Garrison
Keyword(s):  
Decision Making ◽  
Foreign Policy ◽  
Small Group ◽  
Small Groups ◽  
Policy Decision ◽  
Policy Outcomes ◽  
Starting Point ◽  
Group Members ◽  
Policy Decision Making ◽  
High Level

The core decision-making literature argues that leaders and their advisors operate within a political and social context that determines when and how they matter to foreign policy decision making. Small groups and powerful leaders become important when they have an active interest in and involvement with the issue under discussion; when the problem is perceived to be a crisis and important to the future of the regime; in novel situations requiring more than simple application of existing standard operating procedures; and when high-level diplomacy is involved. Irving Janis’s groupthink and Graham Allison’s bureaucratic politics serve as the starting point in the study of small groups and foreign policy decision making. There are three distinct structural arrangements of decision groups: formalistic/hierarchical, competitive, and collegial advisory structures, which vary based on their centralization and how open they are to the input of various members of the decision group. Considering the leader, group members, and influence patterns, it is possible to see that decision making within a group rests on the symbiotic relationship between the leader and members of the group or among group members themselves. Indeed, the interaction among group members creates particular patterns of behavior that affect how the group functions and how the policy process will evolve and likely influence policy outcomes. Ultimately, small group decision making must overcome the consistent challenge to differentiate its role in foreign policy analysis from other decision units and expand further beyond the American context.

Modeling Foreign Policy Decision Making

1970 ◽  
Vol 15 (2) ◽  
pp. 136, 138
Author(s):  
RICHARD L. MERRITT
Keyword(s):  
Decision Making ◽  
Foreign Policy ◽  
Policy Decision ◽  
Policy Decision Making

A CAS Approach to Public Policy Decision Making

1998 ◽  
Author(s):  
Glenda H. Eoyang ◽  
Lois Yellowthunder ◽  
Vic Ward
Keyword(s):  
Public Policy ◽  
Decision Making ◽  
Policy Decision ◽  
Policy Decision Making

Transfer Reinforcement Learning for Autonomous Driving

2021 ◽  
Vol 31 (3) ◽  
pp. 1-26
Author(s):  
Aravind Balakrishnan ◽  
Jaeyoung Lee ◽  
Ashish Gaurav ◽  
Krzysztof Czarnecki ◽  
Sean Sedwards
Keyword(s):  
Decision Making ◽  
Reinforcement Learning ◽  
Transfer Problem ◽  
Autonomous Driving ◽  
High Fidelity ◽  
Rule Based ◽  
High Level ◽  
Real Vehicle

Reinforcement learning (RL) is an attractive way to implement high-level decision-making policies for autonomous driving, but learning directly from a real vehicle or a high-fidelity simulator is variously infeasible. We therefore consider the problem of transfer reinforcement learning and study how a policy learned in a simple environment using WiseMove can be transferred to our high-fidelity simulator, W ise M ove . WiseMove is a framework to study safety and other aspects of RL for autonomous driving. W ise M ove accurately reproduces the dynamics and software stack of our real vehicle. We find that the accurately modelled perception errors in W ise M ove contribute the most to the transfer problem. These errors, when even naively modelled in WiseMove , provide an RL policy that performs better in W ise M ove than a hand-crafted rule-based policy. Applying domain randomization to the environment in WiseMove yields an even better policy. The final RL policy reduces the failures due to perception errors from 10% to 2.75%. We also observe that the RL policy has significantly less reliance on velocity compared to the rule-based policy, having learned that its measurement is unreliable.

Sign in / Sign up

Export Citation Format

Share Document