Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model
This work addresses the problem of sample inefficiency in reinforcement learning for robotics and control systems, offering a novel integration of stochastic models and RL, though it is incremental in combining existing techniques.
The paper tackles the challenge of learning policies from high-dimensional image observations in deep reinforcement learning by separating representation learning from task learning, resulting in the SLAC algorithm that outperforms existing methods in final performance and sample efficiency on complex continuous control tasks.
Deep reinforcement learning (RL) algorithms can use high-capacity deep networks to learn directly from image observations. However, these high-dimensional observation spaces present a number of challenges in practice, since the policy must now solve two problems: representation learning and task learning. In this work, we tackle these two problems separately, by explicitly learning latent representations that can accelerate reinforcement learning from images. We propose the stochastic latent actor-critic (SLAC) algorithm: a sample-efficient and high-performing RL algorithm for learning policies for complex continuous control tasks directly from high-dimensional image inputs. SLAC provides a novel and principled approach for unifying stochastic sequential models and RL into a single method, by learning a compact latent representation and then performing RL in the model's learned latent space. Our experimental evaluation demonstrates that our method outperforms both model-free and model-based alternatives in terms of final performance and sample efficiency, on a range of difficult image-based control tasks. Our code and videos of our results are available at our website.