META-Learning Eligibility Traces for More Sample Efficient Temporal Difference Learning
Temporal-Difference (TD) learning is a standard and very successful reinforcement learning approach, at the core of both algorithms that learn the value of a given policy, as well as algorithms which learn how to improve policies. TD-learning with eligibility traces provides a way to do temporal credit assignment, i.e. decide which portion of a reward should be assigned to predecessor states that occurred at different previous times, controlled by a parameter $\lambda$. However, tuning this parameter can be time-consuming, and not tuning it can lead to inefficient learning. To improve the sample efficiency of TD-learning, we propose a meta-learning method for adjusting the eligibility trace parameter, in a state-dependent manner. The adaptation is achieved with the help of auxiliary learners that learn distributional information about the update targets online, incurring roughly the same computational complexity per step as the usual value learner. Our approach can be used both in on-policy and off-policy learning. We prove that, under some assumptions, the proposed method improves the overall quality of the update targets, by minimizing the overall target error. This method can be viewed as a plugin which can also be used to assist prediction with function approximation by meta-learning feature (observation)-based $\lambda$ online, or even in the control case to assist policy improvement. Our empirical evaluation demonstrates significant performance improvements, as well as improved robustness of the proposed algorithm to learning rate variation.
Code (1)
Tasks
Meta-LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
META-Learning State-based Eligibility Traces for More Sample-Efficient Policy Evaluation
Temporal-Difference (TD) learning is a standard and very successful reinforcement learning approach, at the core of both algorithms that learn the value of a given policy, as well as algorithms which learn how to improve…
Meta-LearningReinforcement LearningAdaptive and Multiple Time-scale Eligibility Traces for Online Deep Reinforcement Learning
Deep reinforcement learning (DRL) is one promising approach to teaching robots to perform complex tasks. Because methods that directly reuse the stored experience data cannot follow the change of the environment in robot…
Deep Reinforcement Learningreinforcement-learningReinforcement Learning (RL)Learning From the Past with Cascading Eligibility Traces
Animals often receive information about errors and rewards after a significant delay. For example, there is typically a delay of tens to hundreds of milliseconds between motor actions and visual feedback. The standard ap…
Beyond Uniform Credit Assignment: Selective Eligibility Traces for RLVR
Reinforcement Learning with Verifiable Rewards (RLVR) has become a key approach for improving the reasoning abilities of large language models. However, widely used critic-free algorithms such as Group Relative Policy Op…
Reinforcement LearningOne-shot learning and behavioral eligibility traces in sequential decision making
In many daily tasks we make multiple decisions before reaching a goal. In order to learn such sequences of decisions, a mechanism to link earlier actions to later reward is necessary. Reinforcement learning theory sugges…
Decision MakingLearning TheoryOne-Shot LearningPupil Dilation+4