Dinerdash Gym: A Benchmark For Policy Learning In High-dimensional Action Space

Abstract

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 design

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keychen2020dinerdash

Related papers

• CANDID DAC: Leveraging Coupled Action Dimensions With Importance Differences In DAC (2024)0.00
• Marginal Policy Gradients: A Unified Family Of Estimators For Bounded Action Spaces With Applications (2018)0.00
• Factored Policy Gradients: Leveraging Structure For Efficient Learning In Momdps (2021)0.00
• Bayesian Off-policy Evaluation And Learning For Large Action Spaces (2024)0.00
• Ensemble Reinforcement Learning In Continuous Spaces -- A Hierarchical Multi-step Approach For Policy Training (2022)2.26
• Deep Multi-agent Reinforcement Learning With Discrete-continuous Hybrid Action Spaces (2019)12.47
• Benchmark Environments For Multitask Learning In Continuous Domains (2017)0.00
• Low-dimensional State And Action Representation Learning With MDP Homomorphism Metrics (2021)0.00