Co-adaptation of algorithmic and implementational innovations in inference-based deep reinforcement learning

概要

Recently many algorithms were devised for reinforcement learning (RL) with function approximation. While they have clear algorithmic distinctions, they also have many implementation differences that are algorithm-independent and sometimes under-emphasized. Such mixing of algorithmic novelty and implementation craftsmanship makes rigorous analyses of the sources of performance improvements across algorithms difficult. In this work, we focus on a series of off-policy inference-based actor-critic algorithms – MPO, AWR, and SAC – to decouple their algorithmic innovations and implementation decisions. We present unified derivations through a single control-as-inference objective, where we can categorize each algorithm as based on either Expectation-Maximization (EM) or direct Kullback-Leibler (KL) divergence minimization and treat the rest of specifications as implementation details. We performed extensive ablation studies, and identified substantial performance drops whenever implementation details are mismatched for algorithmic choices. These results show which implementation details are co-adapted and co-evolved with algorithms, and which are transferable across algorithms: as examples, we identified that tanh Gaussian policy and network sizes are highly adapted to algorithmic types, while layer normalization and ELU are critical for MPO’s performances but also transfer to noticeable gains in SAC. We hope our work can inspire future work to further demystify sources of performance improvements across multiple algorithms and allow researchers to build on one another’s both algorithmic and implementational innovations.

収録
Advances in neural information processing systems
古田 拓毅
古田 拓毅
博士課程
松嶋 達也
松嶋 達也
特任研究員

人間と共生できるような適応的なロボットの開発と,そのようなロボットを作ることにより生命性や知能を構成的に理解することに興味があります.

顧 世翔
顧 世翔
客員准教授