Research map / Reinforcement learning / Visual and representation RL
RLtools: A Fast, Portable Deep Reinforcement Learning Library for Continuous Control
Jonas Eschmann, Dario Albani, Giuseppe Loianno
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Optimize inference code further (fused activations) over generic RLtools implementation | RLtools inference · Crazyflie | inference time: 743 us -> 293 us | Improved |
| Dispatch to manufacturer DSP library instead of generic implementation | RLtools inference · ESP32 (Xtensa) | inference time: 4282 us -> 279 us | Improved |
| Use RLtools optimized instead of DSP library | RLtools inference · ESP32 (Xtensa) | inference time: 279 us -> 333 us | Hurt |
| Optimized code vs DSP library on Teensy 4.1 | RLtools inference · Teensy 4.1 | inference time: 45 us -> 41 us | Improved |
| Enable compiler optimization -O3 instead of -O0 (ablation) | RLtools SAC · Pendulum-v1 training time | training time | Improved |
| Use C++ Pendulum dynamics instead of Python-speed environment (ablation) | RLtools SAC · Pendulum-v1 training time | training time | Improved |
| Enable AVX/AVX2 SIMD instructions (ablation) | RLtools SAC · Pendulum-v1 training time | training time | Improved |
| Enable -ffast-math and oneMKL BLAS (ablation) | RLtools SAC · Pendulum-v1 training time | training time | Improved |
Closest papers by meaning
- SRL: Scaling Distributed Reinforcement Learning to Over Ten Thousand Cores (ICLR 2024 · similarity 0.89)
- Towards General-Purpose Model-Free Reinforcement Learning (ICLR 2025 · similarity 0.87)
- Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes (AAAI 2025 · similarity 0.87)
- TorchRL: A data-driven decision-making library for PyTorch (ICLR 2024 · similarity 0.86)
- RL-GPT: Integrating Reinforcement Learning and Code-as-policy (NeurIPS 2024 · similarity 0.86)
- Overcoming Slow Decision Frequencies in Continuous Control: Model-Based Sequence Reinforcement Learning for Model-Free Control (ICLR 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
