Continual Task Learning through Adaptive Policy Self-Composition

• URL: http://arxiv.org/abs/2411.11364v1
• Date: Mon, 18 Nov 2024 08:20:21 GMT
• Title: Continual Task Learning through Adaptive Policy Self-Composition
• Authors: Shengchao Hu, Yuhang Zhou, Ziqing Fan, Jifeng Hu, Li Shen, Ya Zhang, Dacheng Tao,
• Abstract summary: CompoFormer is a structure-based continual transformer model that adaptively composes previous policies via a meta-policy network. Our experiments reveal that CompoFormer outperforms conventional continual learning (CL) methods, particularly in longer task sequences.
• Score: 54.95680427960524
• License:
• Abstract: Training a generalizable agent to continually learn a sequence of tasks from offline trajectories is a natural requirement for long-lived agents, yet remains a significant challenge for current offline reinforcement learning (RL) algorithms. Specifically, an agent must be able to rapidly adapt to new tasks using newly collected trajectories (plasticity), while retaining knowledge from previously learned tasks (stability). However, systematic analyses of this setting are scarce, and it remains unclear whether conventional continual learning (CL) methods are effective in continual offline RL (CORL) scenarios. In this study, we develop the Offline Continual World benchmark and demonstrate that traditional CL methods struggle with catastrophic forgetting, primarily due to the unique distribution shifts inherent to CORL scenarios. To address this challenge, we introduce CompoFormer, a structure-based continual transformer model that adaptively composes previous policies via a meta-policy network. Upon encountering a new task, CompoFormer leverages semantic correlations to selectively integrate relevant prior policies alongside newly trained parameters, thereby enhancing knowledge sharing and accelerating the learning process. Our experiments reveal that CompoFormer outperforms conventional CL methods, particularly in longer task sequences, showcasing a promising balance between plasticity and stability.

Related papers

• Temporal-Difference Variational Continual Learning [89.32940051152782]
  A crucial capability of Machine Learning models in real-world applications is the ability to continuously learn new tasks. In Continual Learning settings, models often struggle to balance learning new tasks with retaining previous knowledge. We propose new learning objectives that integrate the regularization effects of multiple previous posterior estimations.
  arXiv  Detail & Related papers  (2024-10-10T10:58:41Z)
• Offline Reinforcement Learning from Datasets with Structured Non-Stationarity [50.35634234137108]
  Current Reinforcement Learning (RL) is often limited by the large amount of data needed to learn a successful policy. We address a novel Offline RL problem setting in which, while collecting the dataset, the transition and reward functions gradually change between episodes but stay constant within each episode. We propose a method based on Contrastive Predictive Coding that identifies this non-stationarity in the offline dataset, accounts for it when training a policy, and predicts it during evaluation.
  arXiv  Detail & Related papers  (2024-05-23T02:41:36Z)
• Towards Robust Continual Learning with Bayesian Adaptive Moment Regularization [51.34904967046097]
  Continual learning seeks to overcome the challenge of catastrophic forgetting, where a model forgets previously learnt information. We introduce a novel prior-based method that better constrains parameter growth, reducing catastrophic forgetting. Results show that BAdam achieves state-of-the-art performance for prior-based methods on challenging single-headed class-incremental experiments.
  arXiv  Detail & Related papers  (2023-09-15T17:10:51Z)
• Continual Learners are Incremental Model Generalizers [70.34479702177988]
  This paper extensively studies the impact of Continual Learning (CL) models as pre-trainers. We find that the transfer quality of the representation often increases gradually without noticeable degradation in fine-tuning performance. We propose a new fine-tuning scheme, GLobal Attention Discretization (GLAD), that preserves rich task-generic representation during solving downstream tasks.
  arXiv  Detail & Related papers  (2023-06-21T05:26:28Z)
• Online Continual Learning via the Knowledge Invariant and Spread-out Properties [4.109784267309124]
  Key challenge in continual learning is catastrophic forgetting. We propose a new method, named Online Continual Learning via the Knowledge Invariant and Spread-out Properties (OCLKISP) We empirically evaluate our proposed method on four popular benchmarks for continual learning: Split CIFAR 100, Split SVHN, Split CUB200 and Split Tiny-Image-Net.
  arXiv  Detail & Related papers  (2023-02-02T04:03:38Z)
• Scalable Adversarial Online Continual Learning [11.6720677621333]
  This paper proposes a scalable adversarial continual learning (SCALE) method. It puts forward a parameter generator transforming common features into task-specific features and a single discriminator in the adversarial game to induce common features. It outperforms prominent baselines with noticeable margins in both accuracy and execution time.
  arXiv  Detail & Related papers  (2022-09-04T08:05:40Z)
• Dynamics-Adaptive Continual Reinforcement Learning via Progressive Contextualization [29.61829620717385]
  Key challenge of continual reinforcement learning (CRL) in dynamic environments is to promptly adapt the RL agent's behavior as the environment changes over its lifetime. DaCoRL learns a context-conditioned policy using progressive contextualization. DaCoRL features consistent superiority over existing methods in terms of the stability, overall performance and generalization ability.
  arXiv  Detail & Related papers  (2022-09-01T10:26:58Z)
• Task-Agnostic Online Reinforcement Learning with an Infinite Mixture of Gaussian Processes [25.513074215377696]
  This paper proposes a continual online model-based reinforcement learning approach. It does not require pre-training to solve task-agnostic problems with unknown task boundaries. In experiments, our approach outperforms alternative methods in non-stationary tasks.
  arXiv  Detail & Related papers  (2020-06-19T23:52:45Z)
• Conservative Q-Learning for Offline Reinforcement Learning [106.05582605650932]
  We show that CQL substantially outperforms existing offline RL methods, often learning policies that attain 2-5 times higher final return. We theoretically show that CQL produces a lower bound on the value of the current policy and that it can be incorporated into a policy learning procedure with theoretical improvement guarantees.
  arXiv  Detail & Related papers  (2020-06-08T17:53:42Z)

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.