Revisiting Bisimulation Metric for Robust Representations in Reinforcement Learning
This work addresses representation learning problems in reinforcement learning for researchers, offering incremental improvements to an existing method.
The paper tackled issues in the bisimulation metric for reinforcement learning, such as imprecise reward gap definitions and reliance on predefined weights, by proposing a revised metric with adaptive coefficients and theoretical guarantees, achieving improved performance on DeepMind Control and Meta-World benchmarks.
Bisimulation metric has long been regarded as an effective control-related representation learning technique in various reinforcement learning tasks. However, in this paper, we identify two main issues with the conventional bisimulation metric: 1) an inability to represent certain distinctive scenarios, and 2) a reliance on predefined weights for differences in rewards and subsequent states during recursive updates. We find that the first issue arises from an imprecise definition of the reward gap, whereas the second issue stems from overlooking the varying importance of reward difference and next-state distinctions across different training stages and task settings. To address these issues, by introducing a measure for state-action pairs, we propose a revised bisimulation metric that features a more precise definition of reward gap and novel update operators with adaptive coefficient. We also offer theoretical guarantees of convergence for our proposed metric and its improved representation distinctiveness. In addition to our rigorous theoretical analysis, we conduct extensive experiments on two representative benchmarks, DeepMind Control and Meta-World, demonstrating the effectiveness of our approach.