R2D-RL supplies a Python MARL interface to RCSS2D with shared-memory sync, scenario and full-field support, EPV rewards, and baseline results.
Juliani, V .-P
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
abstract
Recent advances in artificial intelligence have been driven by the presence of increasingly realistic and complex simulated environments. However, many of the existing environments provide either unrealistic visuals, inaccurate physics, low task complexity, restricted agent perspective, or a limited capacity for interaction among artificial agents. Furthermore, many platforms lack the ability to flexibly configure the simulation, making the simulated environment a black-box from the perspective of the learning system. In this work, we propose a novel taxonomy of existing simulation platforms and discuss the highest level class of general platforms which enable the development of learning environments that are rich in visual, physical, task, and social complexity. We argue that modern game engines are uniquely suited to act as general platforms and as a case study examine the Unity engine and open source Unity ML-Agents Toolkit. We then survey the research enabled by Unity and the Unity ML-Agents Toolkit, discussing the kinds of research a flexible, interactive and easily configurable general platform can facilitate.
citation-role summary
background 1
dataset 1
citation-polarity summary
representative citing papers
Three collision-based methods for generating enemy morphologies in games perform as well or better than an evolutionary robotics baseline.
ARC-RL is a new suite of four MuJoCo continuous-control environments featuring game-inspired hexapod and quadruped morphologies, a single closed-form multi-component reward function, CPG demonstrators, and empirical comparisons of online and offline-to-online RL algorithms.
Infernux is a game engine that uses batch data bridging and Numba JIT to make Python scripting performant within a Vulkan C++ core.
FootsiesGym is an open-source, vectorized fighting-game benchmark for two-player zero-sum imperfect-information RL that isolates non-transitive neutral-game dynamics while remaining tractable on standard hardware.
REAP trains an end-to-end SAC policy with behavior cloning and collision penalties inside a 3DGS Real2Sim simulator and transfers it to physical vehicles, succeeding in narrow mechanical parking slots.
A C++ Dec-POMDP simulator using data-oriented design and zero-copy PyTorch integration achieves up to 33 million steps per second on a 16-core CPU, enabling multi-agent policy training in minutes with PPO, DQN, and SAC.
An empirical literature analysis reveals a bifurcation in RL environments into Semantic Prior (LLM-dominated) and Domain-Specific Generalization ecosystems with distinct cognitive fingerprints.
SPDL combined with SAC improves training speed, lap times, and stability over plain SAC for autonomous superbike racing across multiple tracks and models in simulation.
ORRB is an open-source remote rendering backend that pairs Unity3d with MuJoCo for high-throughput, customizable visual domain randomization in robotics environments.
A survey reviewing the architecture, usage patterns, and limitations of NVIDIA Isaac Sim across robotics domains.
The paper delivers a concise, self-contained tutorial on foundational DRL algorithms including REINFORCE and PPO and DIL methods including behavioral cloning, DAgger, and GAIL for embodied agents.
citing papers explorer
-
R2D-RL: A RoboCup 2D Soccer Environment for Multi-Agent Reinforcement Learning
R2D-RL supplies a Python MARL interface to RCSS2D with shared-memory sync, scenario and full-field support, EPV rewards, and baseline results.
-
An Exploration of Collision-based Enemy Morphology Generation
Three collision-based methods for generating enemy morphologies in games perform as well or better than an evolutionary robotics baseline.
-
ARC-RL: A Reinforcement Learning Playground Inspired by ARC Raiders
ARC-RL is a new suite of four MuJoCo continuous-control environments featuring game-inspired hexapod and quadruped morphologies, a single closed-form multi-component reward function, CPG demonstrators, and empirical comparisons of online and offline-to-online RL algorithms.
-
Infernux: A Python-Native Game Engine with JIT-Accelerated Scripting
Infernux is a game engine that uses batch data bridging and Numba JIT to make Python scripting performant within a Vulkan C++ core.
-
FootsiesGym: A Fighting Game Benchmark for Two-Player Zero-Sum Imperfect-Information Games
FootsiesGym is an open-source, vectorized fighting-game benchmark for two-player zero-sum imperfect-information RL that isolates non-transitive neutral-game dynamics while remaining tractable on standard hardware.
-
REAP: Reinforcement-Learning End-to-End Autonomous Parking with Gaussian Splatting Simulator for Real2Sim2Real Transfer
REAP trains an end-to-end SAC policy with behavior cloning and collision penalties inside a 3DGS Real2Sim simulator and transfers it to physical vehicles, succeeding in narrow mechanical parking slots.
-
A High-Throughput Compute-Efficient POMDP Hide-And-Seek-Engine (HASE) for Multi-Agent Operations
A C++ Dec-POMDP simulator using data-oriented design and zero-copy PyTorch integration achieves up to 33 million steps per second on a 16-core CPU, enabling multi-agent policy training in minutes with PPO, DQN, and SAC.
-
From Pixels to Digital Agents: An Empirical Study on the Taxonomy and Technological Trends of Reinforcement Learning Environments
An empirical literature analysis reveals a bifurcation in RL environments into Semantic Prior (LLM-dominated) and Domain-Specific Generalization ecosystems with distinct cognitive fingerprints.
-
Self-Paced Curriculum Reinforcement Learning for Autonomous Superbike Racing in Simulation
SPDL combined with SAC improves training speed, lap times, and stability over plain SAC for autonomous superbike racing across multiple tracks and models in simulation.
-
ORRB -- OpenAI Remote Rendering Backend
ORRB is an open-source remote rendering backend that pairs Unity3d with MuJoCo for high-throughput, customizable visual domain randomization in robotics environments.
-
NVIDIA Isaac Sim: Enabling Scalable, GPU-Accelerated Simulation for Robotics
A survey reviewing the architecture, usage patterns, and limitations of NVIDIA Isaac Sim across robotics domains.
-
An Introduction to Deep Reinforcement and Imitation Learning
The paper delivers a concise, self-contained tutorial on foundational DRL algorithms including REINFORCE and PPO and DIL methods including behavioral cloning, DAgger, and GAIL for embodied agents.