CompetEvo: Towards Morphological Evolution from Competition
Not on the map. Why?
Abstract (arXiv)
Training an agent to adapt to specific tasks through co-optimization of morphology and control has widely attracted attention. However, whether there exists an optimal configuration and tactics for agents in a multiagent competition scenario is still an issue that is challenging to definitively conclude. In this context, we propose competitive evolution (CompetEvo), which co-evolves agents' designs and tactics in confrontation. We build arenas consisting of three animals and their evolved derivatives, placing agents with different morphologies in direct competition with each other. The results reveal that our method enables agents to evolve a more suitable design and strategy for fighting compared to fixed-morph agents, allowing them to obtain advantages in combat scenarios. Moreover, we demonstrate the amazing and impressive behaviors that emerge when confrontations are conducted under asymmetrical morphs.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 17 of its 29 references that are in the map. First posted on arXiv 28 May 2024.
Builds on
17 of 29 references.
References · 17
- 2018Learning by Playing - Solving Sparse Reward Tasks from Scratchcited by 167
- 2021Embodied Intelligence via Learning and Evolutioncited by 163
- 2023Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learningcited by 133
- 2017Emergent Complexity via Multi-Agent Competitioncited by 120
- 2017Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environmentscited by 108
- 2021From Motor Control to Team Play in Simulated Humanoid Footballcited by 87
- 2019Emergent Coordination Through Competitioncited by 57
- 2018Reinforcement Learning for Improving Agent Designcited by 56
- 2018Jointly Learning to Construct and Control Agents using Deep Reinforcement Learningcited by 55
- 2021Transform2Act: Learning a Transform-and-Control Policy for Efficient Agent Designcited by 38
- 2019Neural Graph Evolution: Towards Efficient Automatic Robot Designcited by 36
- 2022GLSO: Grammar-guided Latent Space Optimization for Sample-efficient Robot Design Automationcited by 16
5 more
- 2023Robust multi-agent coordination via evolutionary generation of auxiliary adversarial attackerscited by 15
- 2024Task2Morph: Differentiable Task-inspired Framework for Contact-Aware Robot Designcited by 4
- 2022A Multi-modal Deformable Land-air Robot for Complex Environmentscited by 2
- 2022Coupled Modeling and Fusion Control for a Multi-modal Deformable Land-air Robotcited by 1
- 2024Stimulate the Potential of Robots via Competitioncited by 1
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.