Half Field Offense: An Environment for Multiagent Learning and Ad Hoc Teamwork

By M. Stone. 2016

89 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning (2017, neutral): “This differs from standard multi-agent settings such as Packet World (Weyns et al., 2005) and simulated RoboCup (Hausknecht et al., 2016), where often entire episodes can be fully replayed and analysed.”
The StarCraft Multi-Agent Challenge (2019, background): “This domain was later extended to the Half Field Offense task (Kalyanakrishnan et al., 2006; Hausknecht et al., 2016), which increases the difﬁculty of the problem by requiring the agents to not only keep the ball within bounds but also to score a goal.”
Deep Multi-Agent Reinforcement Learning with Discrete-Continuous Hybrid Action Spaces (2019, background): “However, very often the action space in real world is discrete-continuous hybrid, such as Robot soccer [Hausknecht, 2016; Masson et al. , 2016] and Real Time Strategic (RTS) games [Xiong et al. , 2018].”
Autonomous agents modelling other agents: A comprehensive survey and open problems (2017, background): “Barrett and Stone (2015) consider a similar setting in the Half-Field Offense domain (Hausknecht et al., 2016) and use reinforcement learning to learn optimal collaboration policies for the pickup player in a range of previously encountered teams.”
Learning to Repeat: Fine Grained Action Repetition for Deep Reinforcement Learning (2017, unknown): “…domain [Bellemare et al. (2013); Mnih et al. (2015); Schaul et al. (2015); Mnih et al. (2016)], Mujoco simulated physics tasks domain [Todorov et al. (2012); Lillicrap et al. (2015)], the Robosoccer domain [Hausknecht et al. (2016)] and the TORCS domain [Wymann et al. (2000); Mnih et al. (2016)].”
A Q-values Sharing Framework for Multi-agent Reinforcement Learning under Budget Constraint (2020, background): “Half Field Offense (HFO) [34] is a subtask of simulated robot soccer game.”
Pommerman: A Multi-Agent Playground (2018, background): “Another, more recent, benchmark is Half-Field Offense (Hausknecht et al. 2016), a modification of RoboCup that reduces the complexity and focuses on decision-making in a simplified subtask.”
Dynamic Action Repetition for Deep Reinforcement Learning (2017, methodology): “2013) and Half Field Offensive (Hausknecht et al. 2016) have served as a test bed to measure performance of learning algorithms in AI-based game playing.”