Plasticine: Accelerating Research in Plasticity-Motivated Deep Reinforcement Learning
This work addresses the lack of unified benchmarks for plasticity optimization in deep RL, which is crucial for developing lifelong learning agents, though it is incremental as it builds on existing methods.
The authors tackled the problem of plasticity loss in deep reinforcement learning by introducing Plasticine, an open-source framework that provides benchmarks, implementations of over 13 mitigation methods, and evaluation metrics, enabling systematic analysis and quantification of plasticity dynamics.
Developing lifelong learning agents is crucial for artificial general intelligence. However, deep reinforcement learning (RL) systems often suffer from plasticity loss, where neural networks gradually lose their ability to adapt during training. Despite its significance, this field lacks unified benchmarks and evaluation protocols. We introduce Plasticine, the first open-source framework for benchmarking plasticity optimization in deep RL. Plasticine provides single-file implementations of over 13 mitigation methods, 10 evaluation metrics, and learning scenarios with increasing non-stationarity levels from standard to open-ended environments. This framework enables researchers to systematically quantify plasticity loss, evaluate mitigation strategies, and analyze plasticity dynamics across different contexts. Our documentation, examples, and source code are available at https://github.com/RLE-Foundation/Plasticine.