Combating Reinforcement Learning's Sisyphean Curse with Intrinsic Fear

By Zachary Chase Lipton, Jianfeng Gao, Lihong Li, Jianshu Chen, Li Deng. 2016

55 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Reinforcement Learning

Citations in the corpus

Surprising Negative Results for Generative Adversarial Tree Search (2018, background): “However, in real-world applications, such as robotics (Levine et al., 2016) and dialogue systems (Lipton et al., 2016), collecting samples often takes considerable time and effort.”
Selective Experience Replay for Lifelong Learning (2018, background): “A network may experience forgetting on a single task if rarely occurring events fall out of the buffer (Lipton et al. 2016) or if the network converges to behavior that does not consistently visit the state space (de Bruin et al.”
Troubling Trends in Machine Learning Scholarship (2018, background): “This often manifests in anthropomorphic characterizations of tasks ( reading comprehension [31] and music composition [59]) and techniques ( curiosity [ 66] and fear [48]).”
Go-Explore: a New Approach for Hard-Exploration Problems (2019, background): “Such a catastrophe collection could then be leveraged to train agents that act more carefully in the real world, especially while learning [84, 85].”
AI Safety Gridworlds (2017, background): “Alternatively, we could learn a ‘fail-safe’ policy that overrides the agent’s actions whenever the safety constraint is about to be violated (Saunders et al., 2017), or learn a shaping reward that turns the agent away from bad states (Lipton et al., 2016).”
Learning to Walk in the Real World with Minimal Human Effort (2020, background): “Many researchers have proposed extensions of the existing deep RL algorithms to address safety, such as learning an additional safety layer that projects raw actions to a safe feasibility set [3, 25, 20, 17], learning the boundary of the safe states with a classifier [38, 49, 23], expanding the iden”
AGI Safety Literature Review (2018, unknown): “A similar ideas was explored by Lipton et al. (2016).”
Agent-Agnostic Human-in-the-Loop Reinforcement Learning (2017, background): “The following results all concern Tabular MDPs, but are intended to offer intuition for high-dimensional or continuous environments as well.”
Towards Safe Artificial General Intelligence (2018, background): “A similar ideas was explored by Lipton et al. (2016). Instead of using human-generated labels, their catastrophe detector was trained automatically on the agent’s catastrophes.”
Learn What Not to Learn: Action Elimination with Deep Reinforcement Learning (2018, background): “Lipton et al. (2016a) studied a related problem where an agent wants to avoid catastrophic forgetting of dangerous states.”