DeepAI AI Chat
Log In Sign Up

Learning Dynamics and Generalization in Reinforcement Learning

by   Clare Lyle, et al.

Solving a reinforcement learning (RL) problem poses two competing challenges: fitting a potentially discontinuous value function, and generalizing well to new observations. In this paper, we analyze the learning dynamics of temporal difference algorithms to gain novel insight into the tension between these two objectives. We show theoretically that temporal difference learning encourages agents to fit non-smooth components of the value function early in training, and at the same time induces the second-order effect of discouraging generalization. We corroborate these findings in deep RL agents trained on a range of environments, finding that neural networks trained using temporal difference algorithms on dense reward tasks exhibit weaker generalization between states than randomly initialized networks and networks trained with policy gradient methods. Finally, we investigate how post-training policy distillation may avoid this pitfall, and show that this approach improves generalization to novel environments in the ProcGen suite and improves robustness to input perturbations.


page 5

page 19

page 23


Parameter-based Value Functions

Learning value functions off-policy is at the core of modern Reinforceme...

Comparison of Reinforcement Learning algorithms applied to the Cart Pole problem

Designing optimal controllers continues to be challenging as systems are...

Interference and Generalization in Temporal Difference Learning

We study the link between generalization and interference in temporal-di...

Understanding and Preventing Capacity Loss in Reinforcement Learning

The reinforcement learning (RL) problem is rife with sources of non-stat...

Rethinking Value Function Learning for Generalization in Reinforcement Learning

We focus on the problem of training RL agents on multiple training envir...

Dynamics of Temporal Difference Reinforcement Learning

Reinforcement learning has been successful across several applications i...

Return-based Scaling: Yet Another Normalisation Trick for Deep RL

Scaling issues are mundane yet irritating for practitioners of reinforce...