On Multi-Agent Learning in Team Sports Games

Abstract

In recent years, reinforcement learning has been successful in solving video games from Atari to Star Craft II. However, the end-to-end model-free reinforcement learning (RL) is not sample efficient and requires a significant amount of computational resources to achieve superhuman level performance. Model-free RL is also unlikely to produce human-like agents for playtesting and gameplaying AI in the development cycle of complex video games. In this paper, we present a hierarchical approach to training agents with the goal of achieving human-like style and high skill level in team sports games. While this is still work in progress, our preliminary results show that the presented approach holds promise for solving the posed multi-agent learning problem.

arXiv commentPresented at ICML 2019 Workshop on Imitation, Intent, and Interaction (I3). arXiv admin note: substantial text overlap with arXiv:1903.10545

References in corpus (19)

• Prioritized Experience Replay
• Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
• Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
• DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills
• StarCraft II: A New Challenge for Reinforcement Learning
• A Survey and Critique of Multiagent Deep Reinforcement Learning
• Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewards
• Counterfactual Multi-Agent Policy Gradients
• QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning
• Learning Dexterous In-Hand Manipulation
• A Survey of Learning in Multiagent Environments: Dealing with Non-Stationarity
• Multi-Agent Adversarial Inverse Reinforcement Learning
• Generating Multi-Agent Trajectories using Programmatic Weak Supervision
• CM3: Cooperative Multi-goal Multi-stage Multi-agent Reinforcement Learning
• Learning Latent Plans from Play
• Skynet: A Top Deep RL Agent in the Inaugural Pommerman Team Competition
• Winning Isn't Everything: Enhancing Game Development with Intelligent Agents
• On Reinforcement Learning for Full-length Game of StarCraft
• Safer Deep RL with Shallow MCTS: A Case Study in Pommerman

Cited by in corpus (5)

• Navigates Like Me: Understanding How People Evaluate Human-Like AI in Video Games
• Winning Isn't Everything: Enhancing Game Development with Intelligent Agents
• Provably Efficient Cooperative Multi-Agent Reinforcement Learning with Function Approximation
• QVMix and QVMix-Max: Extending the Deep Quality-Value Family of Algorithms to Cooperative Multi-Agent Reinforcement Learning
• Augmenting the action space with conventions to improve multi-agent cooperation in Hanabi