In Deep Reinforcement Learning (RL), it is a challenge to learn representations that do not exhibit catastrophic forgetting or interference in non-stationary environments.

The ability to approach the same problem from different angles is a cornerstone of human intelligence that leads to robust solutions and effective adaptation to problem variations. In contrast, current RL methodologies tend to lead to policies that settle on a single solution to a given problem, making them brittle to problem variations. Replicating human flexibility in reinforcement learning agents is the challenge that we explore in this work.

In the Integrated Circuit (IC) design flow, floorplanning (FP) determines the position and shape of each block.

Recent progress has demonstrated that recurrent reinforcement learning (RL), which consists of a context encoder based on recurrent neural networks (RNNs) for unobservable state prediction and a multilayer perceptron (MLP) policy for decision making, can mitigate partial observability and serve as a robust baseline for POMDP tasks.

In addition, we build a superiority-based DRL algorithm.

The significant difference between the deployment-time partners' distribution and the training partners' distribution determined by the

Figure 1: Complex decision problems that require a good understanding of the environment's