ODE-based Recurrent Model-free Reinforcement Learning for POMDPs
This work addresses the challenge of partial observability in reinforcement learning for agents in continuous control and meta-RL domains, representing an incremental improvement by integrating ODEs with existing model-free frameworks.
The paper tackled the problem of inferring unseen information in partially observable environments by introducing an ODE-based recurrent model combined with model-free reinforcement learning, demonstrating efficacy across various PO continuous control and meta-RL tasks and robustness against irregular observations.
Neural ordinary differential equations (ODEs) are widely recognized as the standard for modeling physical mechanisms, which help to perform approximate inference in unknown physical or biological environments. In partially observable (PO) environments, how to infer unseen information from raw observations puzzled the agents. By using a recurrent policy with a compact context, context-based reinforcement learning provides a flexible way to extract unobservable information from historical transitions. To help the agent extract more dynamics-related information, we present a novel ODE-based recurrent model combines with model-free reinforcement learning (RL) framework to solve partially observable Markov decision processes (POMDPs). We experimentally demonstrate the efficacy of our methods across various PO continuous control and meta-RL tasks. Furthermore, our experiments illustrate that our method is robust against irregular observations, owing to the ability of ODEs to model irregularly-sampled time series.