paper-with-me

Papers

Semi-Supervised Policy Initialization for Playing Games with Language Hints

2021-06-01 · NAACL 2021 4 · Tsu-Jui Fu, William Yang Wang

Using natural language as a hint can supply an additional reward for playing sparse-reward games. Achieving a goal should involve several different hints, while the given hints are usually incomplete. Those unmentioned latent hints still rely on the sparse reward signal, and make the learning process difficult. In this paper, we propose semi-supervised initialization (SSI) that allows the agent to learn from various possible hints before training under different tasks. Experiments show that SSI not only helps to learn faster (\textbf{1.2x}) but also has a higher success rate (\textbf{11{\%}} relative improvement) of the final policy.

📄 PDF Abstract BibTeX

Code (1)

tsujuifu/code_ssi 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Mobile Networks for Computer Go

2020-08-23 · Tristan Cazenave

The architecture of the neural networks used in Deep Reinforcement Learning programs such as Alpha Zero or Polygames has been shown to have a great impact on the performances of the resulting playing engines. For example…

Deep Reinforcement LearningGame of GoReinforcement Learning (RL)

Towards Playing Full MOBA Games with Deep Reinforcement Learning

2020-11-25 · NeurIPS 2020 12 · Deheng Ye, Guibin Chen, Wen Zhang, Sheng Chen 외

MOBA games, e.g., Honor of Kings, League of Legends, and Dota 2, pose grand challenges to AI systems such as multi-agent, enormous state-action space, complex action control, etc. Developing AI for playing MOBA games has…

AI AgentDeep Reinforcement LearningDota 2reinforcement-learning+2

Supervised Learning Achieves Human-Level Performance in MOBA Games: A Case Study of Honor of Kings

2020-11-25 · Deheng Ye, Guibin Chen, Peilin Zhao, Fuhao Qiu 외

We present JueWu-SL, the first supervised-learning-based artificial intelligence (AI) program that achieves human-level performance in playing multiplayer online battle arena (MOBA) games. Unlike prior attempts, we integ…

A 3D Role-Playing Game for Abusive Language Annotation

2020-05-01 · LREC 2020 5 · Federico Bonetti, Sara Tonelli

Gamification has been applied to many linguistic annotation tasks, as an alternative to crowdsourcing platforms to collect annotated data in an inexpensive way. However, we think that still much has to be explored. Games…

Abusive Language

Deceptive Games

2018-01-31 · Damien Anderson, Matthew Stephenson, Julian Togelius, Christian Salge 외

Deceptive games are games where the reward structure or other aspects of the game are designed to lead the agent away from a globally optimal policy. While many games are already deceptive to some extent, we designed a s…