Combating Reinforcement Learning's Sisyphean Curse with Intrinsic Fear

Understand

Many practical environments contain catastrophic states that an optimal agent would visit infrequently or never.

• Even on toy problems, Deep Reinforcement Learning (DRL) agents tend to periodically revisit these states upon forgetting their existence under a new policy.
• We introduce intrinsic fear (IF), a learned reward shaping that guards DRL agents against periodic catastrophes.
• IF agents possess a fear model trained to predict the probability of imminent catastrophe.