Utilizing Novelty-based Evolution Strategies to Train Transformers in Reinforcement Learning

• URL: http://arxiv.org/abs/2502.06301v2
• Date: Wed, 17 Sep 2025 07:46:50 GMT
• Title: Utilizing Novelty-based Evolution Strategies to Train Transformers in Reinforcement Learning
• Authors: Matyáš Lorenc, Roman Neruda,
• Abstract summary: We evaluate novelty-based variants of OpenAI-ES, the NS-ES and NSR-ES algorithms.<n>We also test if we can accelerate the novelty-based training of these larger models by seeding the training with a pretrained models.
• Score: 1.1868098326257754
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, we experiment with novelty-based variants of OpenAI-ES, the NS-ES and NSR-ES algorithms, and evaluate their effectiveness in training complex, transformer-based architectures designed for the problem of reinforcement learning, such as Decision Transformers. We also test if we can accelerate the novelty-based training of these larger models by seeding the training with a pretrained models. The experimental results were mixed. NS-ES showed progress, but it would clearly need many more iterations for it to yield interesting agents. NSR-ES, on the other hand, proved quite capable of being straightforwardly used on larger models, since its performance appears as similar between the feed-forward model and Decision Transformer, as it was for the OpenAI-ES in our previous work.

Related papers

• Learning Transformer-based World Models with Contrastive Predictive Coding [58.0159270859475]
  We show that the next state prediction objective is insufficient to fully exploit the representation capabilities of Transformers. We propose to extend world model predictions to longer time horizons by introducing TWISTER, a world model using action-conditioned Contrastive Predictive Coding. TWISTER achieves a human-normalized mean score of 162% on the Atari 100k benchmark, setting a new record among state-of-the-art methods that do not employ look-ahead search.
  arXiv  Detail & Related papers  (2025-03-06T13:18:37Z)
• Utilizing Evolution Strategies to Train Transformers in Reinforcement Learning [0.0]
  We explore a capability of evolution strategies to train an agent with its policy based on a transformer architecture in a reinforcement learning setting.<n>We performed experiments using OpenAI's highly parallelizable evolution strategy to train Decision Transformer in Humanoid environment and in Atari games.
  arXiv  Detail & Related papers  (2025-01-23T17:56:40Z)
• Birdie: Advancing State Space Models with Reward-Driven Objectives and Curricula [23.071384759427072]
  State space models (SSMs) offer advantages over Transformers but struggle with tasks requiring long-range in-context retrieval-like text copying, associative recall, and question answering over long contexts.<n>We propose a novel training procedure, Birdie, that significantly enhances the in-context retrieval capabilities of SSMs without altering their architecture.
  arXiv  Detail & Related papers  (2024-11-01T21:01:13Z)
• Supervised Pretraining Can Learn In-Context Reinforcement Learning [96.62869749926415]
  In this paper, we study the in-context learning capabilities of transformers in decision-making problems. We introduce and study Decision-Pretrained Transformer (DPT), a supervised pretraining method where the transformer predicts an optimal action. We find that the pretrained transformer can be used to solve a range of RL problems in-context, exhibiting both exploration online and conservatism offline.
  arXiv  Detail & Related papers  (2023-06-26T17:58:50Z)
• Emergent Agentic Transformer from Chain of Hindsight Experience [96.56164427726203]
  We show that a simple transformer-based model performs competitively with both temporal-difference and imitation-learning-based approaches. This is the first time that a simple transformer-based model performs competitively with both temporal-difference and imitation-learning-based approaches.
  arXiv  Detail & Related papers  (2023-05-26T00:43:02Z)
• Learning to Grow Pretrained Models for Efficient Transformer Training [72.20676008625641]
  We learn to grow pretrained transformers, where we learn to linearly map the parameters of the smaller model to initialize the larger model. Experiments across both language and vision transformers demonstrate that our learned Linear Growth Operator (LiGO) can save up to 50% computational cost of training from scratch.
  arXiv  Detail & Related papers  (2023-03-02T05:21:18Z)
• Exploring Transformers for Behavioural Biometrics: A Case Study in Gait Recognition [0.7874708385247353]
  This article intends to explore and propose novel gait biometric recognition systems based on Transformers. Several state-of-the-art architectures (Vanilla, Informer, Autoformer, Block-Recurrent Transformer, and THAT) are considered in the experimental framework. Experiments are carried out using the two popular public databases whuGAIT and OU-ISIR.
  arXiv  Detail & Related papers  (2022-06-03T08:08:40Z)
• Taming Sparsely Activated Transformer with Stochastic Experts [76.0711573018493]
  Sparsely activated models (SAMs) can easily scale to have outrageously large amounts of parameters without significant increase in computational cost. In this paper, we propose a new expert-based model, THOR (Transformer witH StOchastic ExpeRts) Unlike classic expert-based models, such as the Switch Transformer, experts in THOR are randomly activated for each input during training and inference.
  arXiv  Detail & Related papers  (2021-10-08T17:15:47Z)
• STAR: Sparse Transformer-based Action Recognition [61.490243467748314]
  This work proposes a novel skeleton-based human action recognition model with sparse attention on the spatial dimension and segmented linear attention on the temporal dimension of data. Experiments show that our model can achieve comparable performance while utilizing much less trainable parameters and achieve high speed in training and inference.
  arXiv  Detail & Related papers  (2021-07-15T02:53:11Z)
• Efficient pre-training objectives for Transformers [84.64393460397471]
  We study several efficient pre-training objectives for Transformers-based models. We prove that eliminating the MASK token and considering the whole output during the loss are essential choices to improve performance.
  arXiv  Detail & Related papers  (2021-04-20T00:09:37Z)

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.