Learning to Discover Skills through Guidance
This addresses exploration challenges in unsupervised skill discovery for robotics and AI, though it is an incremental improvement over existing methods.
The paper tackles the problem of limited exploration in unsupervised skill discovery by introducing DISCO-DANCE, which uses guide skills to reach unexplored states and disperses guided skills for discriminability, outperforming baselines in navigation and continuous control benchmarks.
In the field of unsupervised skill discovery (USD), a major challenge is limited exploration, primarily due to substantial penalties when skills deviate from their initial trajectories. To enhance exploration, recent methodologies employ auxiliary rewards to maximize the epistemic uncertainty or entropy of states. However, we have identified that the effectiveness of these rewards declines as the environmental complexity rises. Therefore, we present a novel USD algorithm, skill discovery with guidance (DISCO-DANCE), which (1) selects the guide skill that possesses the highest potential to reach unexplored states, (2) guides other skills to follow guide skill, then (3) the guided skills are dispersed to maximize their discriminability in unexplored states. Empirical evaluation demonstrates that DISCO-DANCE outperforms other USD baselines in challenging environments, including two navigation benchmarks and a continuous control benchmark. Qualitative visualizations and code of DISCO-DANCE are available at https://mynsng.github.io/discodance.