Beyond the Boundaries of Proximal Policy Optimization
Proximal policy optimization (PPO) is a widely-used algorithm for on-policy reinforcement learning. This work offers an alternative perspective of PPO, in which it is decomposed into the inner-loop estimation of update vectors, and the outer-loop application of updates using gradient ascent with unity learning rate. Using this insight we propose outer proximal policy optimization (outer-PPO); a framework wherein these update vectors are applied using an arbitrary gradient-based optimizer. The decoupling of update estimation and update application enabled by outer-PPO highlights several implicit design choices in PPO that we challenge through empirical investigation. In particular we consider non-unity learning rates and momentum applied to the outer loop, and a momentum-bias applied to the inner estimation loop. Methods are evaluated against an aggressively tuned PPO baseline on Brax, Jumanji and MinAtar environments; non-unity learning rates and momentum both achieve statistically significant improvement on Brax and Jumanji, given the same hyperparameter tuning budget.
Code (0)
등록된 구현이 없습니다.
Tasks
UnityMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Sampling Complexity of TD and PPO in RKHS
We revisit Proximal Policy Optimization (PPO) from a function-space perspective. Our analysis decouples policy evaluation and improvement in a reproducing kernel Hilbert space (RKHS): (i) A kernelized temporal-difference…
Stochastic OptimizationDistributed Proximal Policy Optimization for Contention-Based Spectrum Access
The increasing number of wireless devices operating in unlicensed spectrum motivates the development of intelligent adaptive approaches to spectrum access that go beyond traditional carrier sensing. We develop a novel di…
FairnessRiemannian Proximal Policy Optimization
In this paper, We propose a general Riemannian proximal optimization algorithm with guaranteed convergence to solve Markov decision process (MDP) problems. To model policy functions in MDP, we employ Gaussian mixture mod…
Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients
Knowledge distillation transfers a teacher's competence to a small student but is brittle in the small-student regime: forcing the student to imitate logits from a much larger teacher concentrates it on the teacher's sha…
Knowledge DistillationReinforcement LearningProximal Policy Optimization with Mixed Distributed Training
Instability and slowness are two main problems in deep reinforcement learning. Even if proximal policy optimization (PPO) is the state of the art, it still suffers from these two problems. We introduce an improved algori…
Deep Reinforcement LearningReinforcement Learning