Scheduled Policy Optimization for Natural Language Communication with Intelligent Agents
We investigate the task of learning to follow natural language instructions by jointly reasoning with visual observations and language inputs. In contrast to existing methods which start with learning from demonstrations (LfD) and then use reinforcement learning (RL) to fine-tune the model parameters, we propose a novel policy optimization algorithm which dynamically schedules demonstration learning and RL. The proposed training paradigm provides efficient exploration and better generalization beyond existing methods. Comparing to existing ensemble models, the best single model based on our proposed method tremendously decreases the execution error by over 50% on a block-world environment. To further illustrate the exploration strategy of our RL algorithm, We also include systematic studies on the evolution of policy entropy during training.
NurtureToken New!

Token crowdsale for this paper ends in

Buy Nurture Tokens

Authors

Are you an author of this paper? Check the Twitter handle we have for you is correct.

Wenhan Xiong (add twitter)
Xiaoxiao Guo (add twitter)
Mo Yu (add twitter)
Shiyu Chang (add twitter)
Bowen Zhou (add twitter)
William Yang Wang (add twitter)
Ask The Authors

Ask the authors of this paper a question or leave a comment.

Read it. Rate it.
#1. Which part of the paper did you read?

#2. The paper contains new data or analyses that is openly accessible?
#3. The conclusion is supported by the data and analyses?
#4. The conclusion is of scientific interest?
#5. The result is likely to lead to future research?

Github
User:
Stargazers:
6
Forks:
2
Open Issues:
1
Network:
2
Subscribers:
3
Language:
ASP
Implementation of Scheduled Policy Optimization for task-oriented language grouding
Youtube
Link:
None (add)
Views:
0
Likes:
0
Dislikes:
0
Favorites:
0
Comments:
0
Other
Sample Sizes (N=):
Inserted:
Words Total:
Words Unique:
Source:
Abstract:
None
06/23/18 05:05PM
5,785
2,036
Tweets
Nobody has tweeted about this paper.
Images
Related