DinerDash Gym: A Benchmark for Policy Learning in High-Dimensional Action Space

07/13/2020
by   Siwei Chen, et al.
0

It has been arduous to assess the progress of a policy learning algorithm in the domain of hierarchical task with high dimensional action space due to the lack of a commonly accepted benchmark. In this work, we propose a new light-weight benchmark task called Diner Dash for evaluating the performance in a complicated task with high dimensional action space. In contrast to the traditional Atari games that only have a flat structure of goals and very few actions, the proposed benchmark task has a hierarchical task structure and size of 57 for the action space and hence can facilitate the development of policy learning in complicated tasks. On top of that, we introduce Decomposed Policy Graph Modelling (DPGM), an algorithm that combines both graph modelling and deep learning to allow explicit domain knowledge embedding and achieves significant improvement comparing to the baseline. In the experiments, we have shown the effectiveness of the domain knowledge injection via a specially designed imitation algorithm as well as results of other popular algorithms.

READ FULL TEXT
research
07/04/2021

Low-Dimensional State and Action Representation Learning with MDP Homomorphism Metrics

Deep Reinforcement Learning has shown its ability in solving complicated...
research
01/29/2019

Discretizing Continuous Action Space for On-Policy Optimization

In this work, we show that discretizing action space for continuous cont...
research
09/05/2019

Learning Action-Transferable Policy with Action Embedding

Despite achieving great success on performance in various sequential dec...
research
05/28/2013

Reinforcement Learning for the Soccer Dribbling Task

We propose a reinforcement learning solution to the soccer dribbling tas...
research
04/13/2021

Learning and Planning in Complex Action Spaces

Many important real-world problems have action spaces that are high-dime...
research
02/21/2023

MulGT: Multi-task Graph-Transformer with Task-aware Knowledge Injection and Domain Knowledge-driven Pooling for Whole Slide Image Analysis

Whole slide image (WSI) has been widely used to assist automated diagnos...
research
11/10/2020

Untangling Dense Knots by Learning Task-Relevant Keypoints

Untangling ropes, wires, and cables is a challenging task for robots due...

Please sign up or login with your details

Forgot password? Click here to reset