The authors compared evolution strategies (ES) and genetic algorithms (GAs) with PPO, continual-RL variants including TRAC, ReDo and C-CHAIN, and population-based PPO.
Evolution strategies balance adaptation and retention across changing tasks
Across several continual-control benchmarks, neuroevolution retained earlier capabilities while adapting more consistently than gradient-based reinforcement learning variants.
AI Startup
Eleni Nisioti · Andrea Cossu · Kathrin Korte · Sebastian Risi
IT University of Copenhagen · University of Pisa · Sakana AI
Research Digest··2 min read
Nisioti and colleagues test whether neuroevolution, which optimizes populations of neural networks through weight perturbation and selection, can address the tension between learning new tasks and retaining old ones.
Why this paper
From Sakana AI and 2 others
In one line
Neuroevolution, especially evolution strategies, outperforms reinforcement learning methods in continual task settings by achieving a better stability-plasticity trade-off.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§