Comparing Observation and Action Representations for Deep Reinforcement Learning in $μ$RTS

2019-10-26 · Shengyi Huang, Santiago Ontañón

This paper presents a preliminary study comparing different observation and action space representations for Deep Reinforcement Learning (DRL) in the context of Real-time Strategy (RTS) games. Specifically, we compare two representations: (1) a global representation where the observation represents the whole game state, and the RL agent needs to choose which unit to issue actions to, and which actions to execute; and (2) a local representation where the observation is represented from the point of view of an individual unit, and the RL agent picks actions for each unit independently. We evaluate these representations in $\mu$RTS showing that the local representation seems to outperform the global representation when training agents with the task of harvesting resources.

📄 PDF Abstract BibTeX arXiv:1910.12134

Code (4)

vwxyzjn/gym-microrts 공식 구현 pytorch

changpowei/MicroRTS pytorch

farama-foundation/microrts-py pytorch

kered9/gym-microrts pytorch

Tasks

Deep Reinforcement Learningreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Learning Actionable Representations with Goal-Conditioned Policies

2018-11-19 · Dibya Ghosh, Abhishek Gupta, Sergey Levine

Representation learning is a central challenge across a range of machine learning areas. In reinforcement learning, effective and functional representations have the potential to tremendously accelerate learning progress…

Decision Making Hierarchical Reinforcement Learning reinforcement-learning Reinforcement Learning+2

Mapping Instructions and Visual Observations to Actions with Reinforcement Learning

2017-04-28 · EMNLP 2017 9 · Dipendra Misra, John Langford, Yoav Artzi

We propose to directly map raw visual observations and text input to actions for instruction execution. While existing approaches assume access to structured environment representations or use a pipeline of separately tr…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Language Understanding for Text-based Games Using Deep Reinforcement Learning

2015-06-30 · EMNLP 2015 9 · Karthik Narasimhan, tejas kulkarni, Regina Barzilay

In this paper, we consider the task of learning control policies for text-based games. In these games, all interactions in the virtual world are through text and the underlying state is not observed. The resulting langua…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)+1

Learning Actionable Representations with Goal Conditioned Policies

2019-05-01 · ICLR 2019 5 · Dibya Ghosh, Abhishek Gupta, Sergey Levine

Decision Making Hierarchical Reinforcement Learning reinforcement-learning Reinforcement Learning+2

Agent Modelling under Partial Observability for Deep Reinforcement Learning

2020-06-16 · NeurIPS 2021 12 · Georgios Papoudakis, Filippos Christianos, Stefano V. Albrecht

Modelling the behaviours of other agents is essential for understanding how agents interact and making effective decisions. Existing methods for agent modelling commonly assume knowledge of the local observations and cho…

Decoder Deep Reinforcement Learning reinforcement-learning Reinforcement Learning+1