ContainerGym: A Real-World Reinforcement Learning Benchmark for Resource Allocation
This provides a more realistic benchmark for researchers and practitioners in reinforcement learning, though it is incremental as it adapts existing methods to a new domain-specific framework.
The authors tackled the problem of evaluating reinforcement learning algorithms on real-world resource allocation tasks by introducing ContainerGym, a benchmark derived from an industrial problem with minimal simplification. They demonstrated its utility by testing standard baselines like PPO, TRPO, and DQN, revealing limitations in these algorithms through statistical analysis.
We present ContainerGym, a benchmark for reinforcement learning inspired by a real-world industrial resource allocation task. The proposed benchmark encodes a range of challenges commonly encountered in real-world sequential decision making problems, such as uncertainty. It can be configured to instantiate problems of varying degrees of difficulty, e.g., in terms of variable dimensionality. Our benchmark differs from other reinforcement learning benchmarks, including the ones aiming to encode real-world difficulties, in that it is directly derived from a real-world industrial problem, which underwent minimal simplification and streamlining. It is sufficiently versatile to evaluate reinforcement learning algorithms on any real-world problem that fits our resource allocation framework. We provide results of standard baseline methods. Going beyond the usual training reward curves, our results and the statistical tools used to interpret them allow to highlight interesting limitations of well-known deep reinforcement learning algorithms, namely PPO, TRPO and DQN.