DeepAI AI Chat
Log In Sign Up

Self-Adaptive Driving in Nonstationary Environments through Conjectural Online Lookahead Adaptation

by   Tao Li, et al.
NYU college

Powered by deep representation learning, reinforcement learning (RL) provides an end-to-end learning framework capable of solving self-driving (SD) tasks without manual designs. However, time-varying nonstationary environments cause proficient but specialized RL policies to fail at execution time. For example, an RL-based SD policy trained under sunny days does not generalize well to rainy weather. Even though meta learning enables the RL agent to adapt to new tasks/environments, its offline operation fails to equip the agent with online adaptation ability when facing nonstationary environments. This work proposes an online meta reinforcement learning algorithm based on the conjectural online lookahead adaptation (COLA). COLA determines the online adaptation at every step by maximizing the agent's conjecture of the future performance in a lookahead horizon. Experimental results demonstrate that under dynamically changing weather and lighting conditions, the COLA-based self-adaptive driving outperforms the baseline policies in terms of online adaptability. A demo video, source code, and appendixes are available at


Offline Meta-Reinforcement Learning with Online Self-Supervision

Meta-reinforcement learning (RL) can meta-train policies that adapt to n...

Learning a subspace of policies for online adaptation in Reinforcement Learning

Deep Reinforcement Learning (RL) is mainly studied in a setting where th...

From Ember to Blaze: Swift Interactive Video Adaptation via Meta-Reinforcement Learning

Maximizing quality of experience (QoE) for interactive video streaming h...

Evolving Inborn Knowledge For Fast Adaptation in Dynamic POMDP Problems

Rapid online adaptation to changing tasks is an important problem in mac...

Towards Data-Driven Offline Simulations for Online Reinforcement Learning

Modern decision-making systems, from robots to web recommendation engine...

Adaptive Reinforcement Learning through Evolving Self-Modifying Neural Networks

The adaptive learning capabilities seen in biological neural networks ar...

Neurosymbolic Meta-Reinforcement Lookahead Learning Achieves Safe Self-Driving in Non-Stationary Environments

In the area of learning-driven artificial intelligence advancement, the ...