OmniPiano: Diverse Dexterous Piano-Playing Challenges for Standard, Robust, Safe, and Multi-Agent RL
cs.AI
Submitted: 2026-10-30
Updated: 2026-10-30
Project page: https://sail-research-lab.github.io/omnipiano
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- The Hanabi Challenge: A New Frontier for AI Research
- CrossQ: Batch Normalization in Deep Reinforcement Learning for Greater Sample Efficiency and Simplicity
- TorchRL: A data-driven decision-making library for PyTorch
- OpenAI Gym
- Dexterous Robotic Piano Playing at Scale
- Leveraging Procedural Generation to Benchmark Reinforcement Learning
- SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning
- Counterfactual Multi-Agent Policy Gradients
- D4RL: Datasets for Deep Data-Driven Reinforcement Learning
- ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills
- RL Unplugged: A Suite of Benchmarks for Offline Reinforcement Learning
- Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
- Adversarial Attacks on Neural Network Policies
- CANTABILE: Learning Expressive Dynamics for Robotic Piano Performance
- Learning Robust Policy against Disturbance in Transition Dynamics via State-Conservative Policy Optimization
- Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning
- Google Research Football: A Novel Reinforcement Learning Environment
- Automating Control of Overestimation Bias for Reinforcement Learning
- Non-Stationary Markov Decision Processes, a Worst-Case Approach using Model-Based Reinforcement Learning, Extended version
- RLlib: Abstractions for Distributed Reinforcement Learning
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents