Loss is its own Reward: Self-Supervision for Reinforcement Learning
This addresses data efficiency issues in reinforcement learning for tasks with sparse rewards, but it appears incremental as it builds on existing self-supervision methods.
The paper tackles the problem of sparse and delayed rewards in reinforcement learning by introducing self-supervised auxiliary losses based on states, actions, and successors to provide additional supervision. The result shows that this approach improves data efficiency and policy returns, though specific numerical gains are not detailed in the abstract.
Reinforcement learning optimizes policies for expected cumulative reward. Need the supervision be so narrow? Reward is delayed and sparse for many tasks, making it a difficult and impoverished signal for end-to-end optimization. To augment reward, we consider a range of self-supervised tasks that incorporate states, actions, and successors to provide auxiliary losses. These losses offer ubiquitous and instantaneous supervision for representation learning even in the absence of reward. While current results show that learning from reward alone is feasible, pure reinforcement learning methods are constrained by computational and data efficiency issues that can be remedied by auxiliary losses. Self-supervised pre-training and joint optimization improve the data efficiency and policy returns of end-to-end reinforcement learning.