Arena: A General Evaluation Platform and Building Toolkit for Multi-Agent Intelligence
arXiv:1905.08085
Abstract
Learning agents that are not only capable of taking tests, but also innovating is becoming a hot topic in AI. One of the most promising paths towards this vision is multi-agent learning, where agents act as the environment for each other, and improving each agent means proposing new problems for others. However, existing evaluation platforms are either not compatible with multi-agent settings, or limited to a specific game. That is, there is not yet a general evaluation platform for research on multi-agent intelligence. To this end, we introduce Arena, a general evaluation platform for multi-agent intelligence with 35 games of diverse logics and representations. Furthermore, multi-agent intelligence is still at the stage where many problems remain unexplored. Therefore, we provide a building toolkit for researchers to easily invent and build novel multi-agent problems from the provided game set based on a GUI-configurable social tree and five basic multi-agent reward schemes. Finally, we provide Python implementations of five state-of-the-art deep multi-agent reinforcement learning baselines. Along with the baseline implementations, we release a set of 100 best agents/teams that we can train with different training schemes for each game, as the base for evaluating agents with population performance. As such, the research community can perform comparisons under a stable and uniform standard. All the implementations and accompanied tutorials have been open-sourced for the community at https://sites.google.com/view/arena-unity/.
References in corpus (39)
- Learning to Communicate with Deep Multi-Agent Reinforcement Learning
- DeepStack: Expert-Level Artificial Intelligence in No-Limit Poker
- Human-level performance in first-person multiplayer games with population-based deep reinforcement learning
- StarCraft II: A New Challenge for Reinforcement Learning
- A Survey and Critique of Multiagent Deep Reinforcement Learning
- Emergence of Locomotion Behaviours in Rich Environments
- Unity: A General Platform for Intelligent Agents
- DeepMind Control Suite
- Counterfactual Multi-Agent Policy Gradients
- Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning
- QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning
- Matterport3D: Learning from RGB-D Data in Indoor Environments
- AI2-THOR: An Interactive 3D Environment for Visual AI
- Learning Multiagent Communication with Backpropagation
- Multiagent Bidirectionally-Coordinated Nets: Emergence of Human-level Coordination in Learning to Play StarCraft Combat Games
- Building Generalizable Agents with a Realistic and Rich 3D Environment
- Emergence of Grounded Compositional Language in Multi-Agent Populations
- MINOS: Multimodal Indoor Simulator for Navigation in Complex Environments
- A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning
- Deep Reinforcement Learning from Self-Play in Imperfect-Information Games
- Maintaining cooperation in complex social dilemmas using deep reinforcement learning
- Episodic Exploration for Deep Deterministic Policies: An Application to StarCraft Micromanagement Tasks
- ViZDoom Competitions: Playing Doom from Pixels
- Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learning
- Emergent Coordination Through Competition
- HoME: a Household Multimodal Environment
- Gotta Learn Fast: A New Benchmark for Generalization in RL
- Predicting Human Behavior in Unrepeated, Simultaneous-Move Games
- CHALET: Cornell House Agent Learning Environment
- Autocurricula and the Emergence of Innovation from Social Interaction: A Manifesto for Multi-Agent Intelligence Research
- Psychlab: A Psychology Laboratory for Deep Reinforcement Learning Agents
- Neural MMO: A Massively Multiagent Game Environment for Training and Evaluating Intelligent Agents
- Open-ended Learning in Symmetric Zero-sum Games
- DeepMind Lab
- Learning to Play Guess Who? and Inventing a Grounded Language as a Consequence
- Re-evaluating Evaluation
- VirtualHome: Simulating Household Activities via Programs
- Marathon Environments: Multi-Agent Continuous Control Benchmarks in a Modern Video Game Engine
- DeepCrawl: Deep Reinforcement Learning for Turn-based Strategy Games