Research map / Reinforcement learning / Visual and representation RL
Evolution Gym: A Large-Scale Benchmark for Evolving Soft Robots
Jagdeep Singh Bhatia, Holly Jackson, Yunsheng Tian, Jie Xu, Wojciech Matusik
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 |
|---|---|---|---|
| use genetic algorithm for design optimization instead of Bayesian optimization or CPPN-NEAT | co-design with PPO · 10 Evolution Gym tasks | reward curves | Improved |
| use CPPN-NEAT design encoding instead of GA on manipulation tasks | co-design with PPO · manipulation tasks | reward | Hurt |
| use Bayesian optimization for design search | co-design with PPO · most Evolution Gym tasks | reward | Hurt |
| evolve robot design with GA instead of hand-designed bio-inspired robot | robot design · Climber and other tasks | reward | Improved |
| evolve robot design with GA instead of hand-designed robot | robot design · Carrier | reward | No clear effect |
| evolve designs with any baseline co-design algorithm | co-design algorithms · Beam Slider (hard tasks) | task success | No clear effect |
Closest papers by meaning
- Embracing Evolution: A Call for Body-Control Co-Design in Embodied Humanoid Robot (NeurIPS 2026 · similarity 0.90)
- DittoGym: Learning to Control Soft Shape-Shifting Robots (ICLR 2024 · similarity 0.89)
- MorphVAE: Advancing Morphological Design of Voxel-Based Soft Robots with Variational Autoencoders (AAAI 2024 · similarity 0.89)
- Debate2Create: Robot Co-design via Multi-Agent LLM Debate (ICML 2026 · similarity 0.87)
- Convergent Functions, Divergent Forms (NeurIPS 2025 · similarity 0.87)
- BodyGen: Advancing Towards Efficient Embodiment Co-Design (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.
