Improving Computational Efficiency in Visual Reinforcement Learning via Stored Embeddings
This work addresses efficiency issues in visual RL for researchers and practitioners, though it is incremental as it modifies existing off-policy methods.
The paper tackled the high computational and memory demands of visual reinforcement learning by proposing SEER, a method that freezes early CNN layers and stores low-dimensional embeddings in replay buffers, which maintained performance while significantly reducing computation and memory usage across DeepMind Control and Atari environments.
Recent advances in off-policy deep reinforcement learning (RL) have led to impressive success in complex tasks from visual observations. Experience replay improves sample-efficiency by reusing experiences from the past, and convolutional neural networks (CNNs) process high-dimensional inputs effectively. However, such techniques demand high memory and computational bandwidth. In this paper, we present Stored Embeddings for Efficient Reinforcement Learning (SEER), a simple modification of existing off-policy RL methods, to address these computational and memory requirements. To reduce the computational overhead of gradient updates in CNNs, we freeze the lower layers of CNN encoders early in training due to early convergence of their parameters. Additionally, we reduce memory requirements by storing the low-dimensional latent vectors for experience replay instead of high-dimensional images, enabling an adaptive increase in the replay buffer capacity, a useful technique in constrained-memory settings. In our experiments, we show that SEER does not degrade the performance of RL agents while significantly saving computation and memory across a diverse set of DeepMind Control environments and Atari games.