A Study of Plasticity Loss in On-Policy Deep Reinforcement Learning

• URL: http://arxiv.org/abs/2405.19153v2
• Date: Fri, 01 Nov 2024 16:47:59 GMT
• Title: A Study of Plasticity Loss in On-Policy Deep Reinforcement Learning
• Authors: Arthur Juliani, Jordan T. Ash,
• Abstract summary: We show that plasticity loss is pervasive under domain shift in on-policy deep RL. We find that a class of regenerative'' methods are able to consistently mitigate plasticity loss in a variety of contexts.
• Score: 7.767611890997147
• License:
• Abstract: Continual learning with deep neural networks presents challenges distinct from both the fixed-dataset and convex continual learning regimes. One such challenge is plasticity loss, wherein a neural network trained in an online fashion displays a degraded ability to fit new tasks. This problem has been extensively studied in both supervised learning and off-policy reinforcement learning (RL), where a number of remedies have been proposed. Still, plasticity loss has received less attention in the on-policy deep RL setting. Here we perform an extensive set of experiments examining plasticity loss and a variety of mitigation methods in on-policy deep RL. We demonstrate that plasticity loss is pervasive under domain shift in this regime, and that a number of methods developed to resolve it in other settings fail, sometimes even performing worse than applying no intervention at all. In contrast, we find that a class of ``regenerative'' methods are able to consistently mitigate plasticity loss in a variety of contexts, including in gridworld tasks and more challenging environments like Montezuma's Revenge and ProcGen.

Related papers

• Plasticity Loss in Deep Reinforcement Learning: A Survey [15.525552360867367]
  plasticity is crucial for deep Reinforcement Learning (RL) agents. Once plasticity is lost, an agent's performance will plateau because it cannot improve its policy to account for changes in the data distribution. Loss of plasticity can be connected to many other issues plaguing deep RL, such as training instabilities, scaling failures, overestimation bias, and insufficient exploration.
  arXiv  Detail & Related papers  (2024-11-07T16:13:54Z)
• Disentangling the Causes of Plasticity Loss in Neural Networks [55.23250269007988]
  We show that loss of plasticity can be decomposed into multiple independent mechanisms. We show that a combination of layer normalization and weight decay is highly effective at maintaining plasticity in a variety of synthetic nonstationary learning tasks.
  arXiv  Detail & Related papers  (2024-02-29T00:02:33Z)
• Learning fast changing slow in spiking neural networks [3.069335774032178]
  Reinforcement learning (RL) faces substantial challenges when applied to real-life problems. Life-long learning machines must resolve the plasticity-stability paradox. Striking a balance between acquiring new knowledge and maintaining stability is crucial for artificial agents.
  arXiv  Detail & Related papers  (2024-01-25T12:03:10Z)
• Loss of Plasticity in Continual Deep Reinforcement Learning [14.475963928766134]
  We demonstrate that deep RL agents lose their ability to learn good policies when they cycle through a sequence of Atari 2600 games. We investigate this phenomenon closely at scale and analyze how the weights, gradients, and activations change over time. Our analysis shows that the activation footprint of the network becomes sparser, contributing to the diminishing gradients.
  arXiv  Detail & Related papers  (2023-03-13T22:37:15Z)
• Understanding plasticity in neural networks [41.79540750236036]
  Plasticity is the ability of a neural network to quickly change its predictions in response to new information. Deep neural networks are known to lose plasticity over the course of training even in relatively simple learning problems.
  arXiv  Detail & Related papers  (2023-03-02T18:47:51Z)
• Learning Dynamics and Generalization in Reinforcement Learning [59.530058000689884]
  We show theoretically that temporal difference learning encourages agents to fit non-smooth components of the value function early in training. We show that neural networks trained using temporal difference algorithms on dense reward tasks exhibit weaker generalization between states than randomly networks and gradient networks trained with policy methods.
  arXiv  Detail & Related papers  (2022-06-05T08:49:16Z)
• Disturbing Reinforcement Learning Agents with Corrupted Rewards [62.997667081978825]
  We analyze the effects of different attack strategies based on reward perturbations on reinforcement learning algorithms. We show that smoothly crafting adversarial rewards are able to mislead the learner, and that using low exploration probability values, the policy learned is more robust to corrupt rewards.
  arXiv  Detail & Related papers  (2021-02-12T15:53:48Z)
• Deep Reinforcement Learning amidst Lifelong Non-Stationarity [67.24635298387624]
  We show that an off-policy RL algorithm can reason about and tackle lifelong non-stationarity. Our method leverages latent variable models to learn a representation of the environment from current and past experiences. We also introduce several simulation environments that exhibit lifelong non-stationarity, and empirically find that our approach substantially outperforms approaches that do not reason about environment shift.
  arXiv  Detail & Related papers  (2020-06-18T17:34:50Z)
• Understanding the Role of Training Regimes in Continual Learning [51.32945003239048]
  Catastrophic forgetting affects the training of neural networks, limiting their ability to learn multiple tasks sequentially. We study the effect of dropout, learning rate decay, and batch size, on forming training regimes that widen the tasks' local minima.
  arXiv  Detail & Related papers  (2020-06-12T06:00:27Z)
• Learn2Perturb: an End-to-end Feature Perturbation Learning to Improve Adversarial Robustness [79.47619798416194]
  Learn2Perturb is an end-to-end feature perturbation learning approach for improving the adversarial robustness of deep neural networks. Inspired by the Expectation-Maximization, an alternating back-propagation training algorithm is introduced to train the network and noise parameters consecutively.
  arXiv  Detail & Related papers  (2020-03-02T18:27:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.