Prioritized Level Replay

• URL: http://arxiv.org/abs/2010.03934v4
• Date: Sat, 12 Jun 2021 10:50:10 GMT
• Title: Prioritized Level Replay
• Abstract summary: We introduce Prioritized Level Replay (PLR), a framework for selectively sampling the next training level. PLR significantly improves sample efficiency and generalization on Procgen Benchmark.
• Score: 24.980249597326985
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Environments with procedurally generated content serve as important benchmarks for testing systematic generalization in deep reinforcement learning. In this setting, each level is an algorithmically created environment instance with a unique configuration of its factors of variation. Training on a prespecified subset of levels allows for testing generalization to unseen levels. What can be learned from a level depends on the current policy, yet prior work defaults to uniform sampling of training levels independently of the policy. We introduce Prioritized Level Replay (PLR), a general framework for selectively sampling the next training level by prioritizing those with higher estimated learning potential when revisited in the future. We show TD-errors effectively estimate a level's future learning potential and, when used to guide the sampling procedure, induce an emergent curriculum of increasingly difficult levels. By adapting the sampling of training levels, PLR significantly improves sample efficiency and generalization on Procgen Benchmark--matching the previous state-of-the-art in test return--and readily combines with other methods. Combined with the previous leading method, PLR raises the state-of-the-art to over 76% improvement in test return relative to standard RL baselines.

Related papers

• Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning [50.738952715864116]
  Expressive continuous control policies form the backbone of advances in scaling imitation learning for simulated and real robot control.<n>We propose QGF (Q-Guided Flow), an RL algorithm that performs policy optimization entirely at test time.<n> Empirically, QGF outperforms prior test-time RL methods on single-task and goal-conditioned offline RL benchmarks.
  arXiv  Detail & Related papers  (2026-06-09T16:45:57Z)
• How Learning Rate Decay Wastes Your Best Data in Curriculum-Based LLM Pretraining [22.50461083222824]
  A natural approach to better leverage high-quality data is curriculum-based pretraining, where the model is trained on data sorted in ascending order of quality as determined by a quality metric.<n>This work identifies a critical factor constraining these methods: the incompatibility between the ascending data quality order and the decaying learning rate schedule.
  arXiv  Detail & Related papers  (2025-11-24T09:03:49Z)
• Test-time Offline Reinforcement Learning on Goal-related Experience [50.94457794664909]
  Research in foundation models has shown that performance can be substantially improved through test-time training.<n>We propose a novel self-supervised data selection criterion, which selects transitions from an offline dataset according to their relevance to the current state.<n>Our goal-conditioned test-time training (GC-TTT) algorithm applies this routine in a receding-horizon fashion during evaluation, adapting the policy to the current trajectory as it is being rolled out.
  arXiv  Detail & Related papers  (2025-07-24T21:11:39Z)
• From Data-Centric to Sample-Centric: Enhancing LLM Reasoning via Progressive Optimization [7.531052649961168]
  Reinforcement learning with verifiable rewards (RLVR) has recently advanced the reasoning capabilities of large language models (LLMs)<n>We investigate RLVR from a sample-centric perspective and introduce LPPO, a framework of progressive optimization techniques.<n>Our work addresses a critical question: how to best leverage a small set of trusted, high-quality demonstrations, rather than simply scaling up data volume.
  arXiv  Detail & Related papers  (2025-07-09T06:05:28Z)
• Data Normalization Strategies for EEG Deep Learning [0.0]
  We show that optimal normalization strategies differ significantly between training paradigms.<n>Window-level within-channel normalization yields the best performance in supervised tasks.<n>Our findings challenge the assumption that a universal normalization strategy can generalize across learning settings.
  arXiv  Detail & Related papers  (2025-06-15T15:33:41Z)
• Direct Preference Optimization for Primitive-Enabled Hierarchical Reinforcement Learning [75.9729413703531]
  DIPPER is a novel HRL framework that formulates hierarchical policy learning as a bi-level optimization problem.<n>We show that DIPPER achieves up to 40% improvement over state-of-the-art baselines in sparse reward scenarios.
  arXiv  Detail & Related papers  (2024-11-01T04:58:40Z)
• DRED: Zero-Shot Transfer in Reinforcement Learning via Data-Regularised Environment Design [11.922951794283168]
  In this work, we investigate how the sampling of individual environment instances, or levels, affects the zero-shot generalisation (ZSG) ability of RL agents. We discover that for deep actor-critic architectures sharing their base layers, prioritising levels according to their value loss minimises the mutual information between the agent's internal representation and the set of training levels in the generated training data. We find that existing UED methods can significantly shift the training distribution, which translates to low ZSG performance. To prevent both overfitting and distributional shift, we introduce data-regularised environment design (D
  arXiv  Detail & Related papers  (2024-02-05T19:47:45Z)
• Few-Shot Class-Incremental Learning with Prior Knowledge [94.95569068211195]
  We propose Learning with Prior Knowledge (LwPK) to enhance the generalization ability of the pre-trained model. Experimental results indicate that LwPK effectively enhances the model resilience against catastrophic forgetting.
  arXiv  Detail & Related papers  (2024-02-02T08:05:35Z)
• Hierarchical Decomposition of Prompt-Based Continual Learning: Rethinking Obscured Sub-optimality [55.88910947643436]
  Self-supervised pre-training is essential for handling vast quantities of unlabeled data in practice. HiDe-Prompt is an innovative approach that explicitly optimize the hierarchical components with an ensemble of task-specific prompts and statistics. Our experiments demonstrate the superior performance of HiDe-Prompt and its robustness to pre-training paradigms in continual learning.
  arXiv  Detail & Related papers  (2023-10-11T06:51:46Z)
• Policy-Gradient Training of Language Models for Ranking [29.940468096858066]
  Text retrieval plays a crucial role in incorporating factual knowledge for decision making into language processing pipelines. Current state-of-the-art text retrieval models leverage pre-trained large language models (LLMs) to achieve competitive performance. We introduce Neural PG-RANK, a novel training algorithm that learns to rank by instantiating a LLM as a Plackett-Luce ranking policy.
  arXiv  Detail & Related papers  (2023-10-06T17:55:23Z)
• How the level sampling process impacts zero-shot generalisation in deep reinforcement learning [12.79149059358717]
  Key limitation preventing wider adoption of autonomous agents trained via deep reinforcement learning is their limited ability to generalise to new environments. We investigate how a non-uniform sampling strategy of individual environment instances affects the zero-shot generalisation ability of RL agents.
  arXiv  Detail & Related papers  (2023-10-05T12:08:12Z)
• Isolation and Impartial Aggregation: A Paradigm of Incremental Learning without Interference [61.11137714507445]
  This paper focuses on the prevalent performance imbalance in the stages of incremental learning. We propose a stage-isolation based incremental learning framework. We evaluate the proposed method on four large benchmarks.
  arXiv  Detail & Related papers  (2022-11-29T06:57:48Z)
• Adaptive Distribution Calibration for Few-Shot Learning with Hierarchical Optimal Transport [78.9167477093745]
  We propose a novel distribution calibration method by learning the adaptive weight matrix between novel samples and base classes. Experimental results on standard benchmarks demonstrate that our proposed plug-and-play model outperforms competing approaches.
  arXiv  Detail & Related papers  (2022-10-09T02:32:57Z)
• Towards Diverse Evaluation of Class Incremental Learning: A Representation Learning Perspective [67.45111837188685]
  Class incremental learning (CIL) algorithms aim to continually learn new object classes from incrementally arriving data. We experimentally analyze neural network models trained by CIL algorithms using various evaluation protocols in representation learning.
  arXiv  Detail & Related papers  (2022-06-16T11:44:11Z)
• Simple Control Baselines for Evaluating Transfer Learning [1.0499611180329802]
  We share an evaluation standard that aims to quantify and communicate transfer learning performance. We provide an example empirical study investigating a few basic questions about self-supervised learning.
  arXiv  Detail & Related papers  (2022-02-07T17:26:26Z)
• Pre-training Is (Almost) All You Need: An Application to Commonsense Reasoning [61.32992639292889]
  Fine-tuning of pre-trained transformer models has become the standard approach for solving common NLP tasks. We introduce a new scoring method that casts a plausibility ranking task in a full-text format. We show that our method provides a much more stable training phase across random restarts.
  arXiv  Detail & Related papers  (2020-04-29T10:54:40Z)

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.