Deep reinforcement learning (DRL) has achieved great successes in recent years with the help of novel methods and higher compute power. However, there are still several challenges to be addressed such as convergence to locally optimal policies and long training times. In this paper, firstly, we augment Asynchronous Advantage Actor-Critic (A3C) method with a novel self-supervised auxiliary task, i.e. Terminal Prediction, measuring temporal closeness to terminal states, namely A3C-TP. Secondly, we propose a new framework where planning algorithms such as Monte Carlo tree search or other sources of (simulated) demonstrators can be integrated to asynchronous distributed DRL methods. Compared to vanilla A3C, our proposed methods both learn faster and converge to better policies on a two-player mini version of the Pommerman game.
Related Research
-
Leveraging Environment Interaction for Automated PDDL Generation and Planning with Large Language Models
Leveraging Environment Interaction for Automated PDDL Generation and Planning with Large Language Models
S. Mahdavi, R. Aoki, K. Tang, and Y. Cao. Conference on Neural Information Processing System (NeurIPS)
Publications
-
Jump Starting Bandits with LLM-Generated Prior Knowledge
Jump Starting Bandits with LLM-Generated Prior Knowledge
P. A. Alamdari, Y. Cao, and K. Wilson. Conference on Empirical Methods in Natural Language Processing
Publications
-
Our NeurIPS 2021 Reading List
Our NeurIPS 2021 Reading List
Y. Cao, K. Y. C. Lui, T. Durand, J. He, P. Xu, N. Mehrasa, A. Radovic, A. Lehrmann, R. Deng, A. Abdi, M. Schlegel, and S. Liu.
Computer Vision; Data Visualization; Graph Representation Learning; Learning And Generalization; Natural Language Processing; Optimization; Reinforcement Learning; Time series Modelling; Unsupervised Learning
Research