Cautious adaptation for reinforcement learning in safety-critical settings

J Zhang, B Cheung, C Finn, S Levine… - International …, 2020 - proceedings.mlr.press
International Conference on Machine Learning, 2020proceedings.mlr.press
Reinforcement learning (RL) in real-world safety-critical target settings like urban driving is
hazardous, imperiling the RL agent, other agents, and the environment. To overcome this
difficulty, we propose a" safety-critical adaptation" task setting: an agent first trains in non-
safety-critical" source" environments such as in a simulator, before it adapts to the target
environment where failures carry heavy costs. We propose a solution approach, CARL, that
builds on the intuition that prior experience in diverse environments equips an agent to …
Abstract
Reinforcement learning (RL) in real-world safety-critical target settings like urban driving is hazardous, imperiling the RL agent, other agents, and the environment. To overcome this difficulty, we propose a" safety-critical adaptation" task setting: an agent first trains in non-safety-critical" source" environments such as in a simulator, before it adapts to the target environment where failures carry heavy costs. We propose a solution approach, CARL, that builds on the intuition that prior experience in diverse environments equips an agent to estimate risk, which in turn enables relative safety through risk-averse, cautious adaptation. CARL first employs model-based RL to train a probabilistic model to capture uncertainty about transition dynamics and catastrophic states across varied source environments. Then, when exploring a new safety-critical environment with unknown dynamics, the CARL agent plans to avoid actions that could lead to catastrophic states. In experiments on car driving, cartpole balancing, and half-cheetah locomotion, CARL successfully acquires cautious exploration behaviors, yielding higher rewards with fewer failures than strong RL adaptation baselines.
proceedings.mlr.press
以上显示的是最相近的搜索结果。 查看全部搜索结果