Addressing Sample Complexity in Visual Tasks Using HER and Hallucinatory GANs
This work addresses sample efficiency for researchers and practitioners in visual reinforcement learning, though it is incremental as it adapts existing methods to a new domain.
The paper tackles the problem of high sample complexity in reinforcement learning for visual tasks by combining Hindsight Experience Replay with a generative model to hallucinate successful visual trajectories, resulting in marked improvements over baselines in 3D navigation and simulated robotics applications.
Reinforcement Learning (RL) algorithms typically require millions of environment interactions to learn successful policies in sparse reward settings. Hindsight Experience Replay (HER) was introduced as a technique to increase sample efficiency by reimagining unsuccessful trajectories as successful ones by altering the originally intended goals. However, it cannot be directly applied to visual environments where goal states are often characterized by the presence of distinct visual features. In this work, we show how visual trajectories can be hallucinated to appear successful by altering agent observations using a generative model trained on relatively few snapshots of the goal. We then use this model in combination with HER to train RL agents in visual settings. We validate our approach on 3D navigation tasks and a simulated robotics application and show marked improvement over baselines derived from previous work.