Bi-directional Recurrence Improves Transformer in Partially Observable Markov Decision Processes

• URL: http://arxiv.org/abs/2505.11153v1
• Date: Fri, 16 May 2025 11:54:48 GMT
• Title: Bi-directional Recurrence Improves Transformer in Partially Observable Markov Decision Processes
• Authors: Ashok Arora, Neetesh Kumar,
• Abstract summary: This work introduces a novel bi-recurrent model architecture that improves sample efficiency and reduces model parameter count in POMDP scenarios.<n>The proposed model architecture outperforms existing transformer-based, attention-based, and recurrence-based methods by a margin ranging from 87.39% to 482.04% on average.
• Score: 5.220940151628735
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In real-world reinforcement learning (RL) scenarios, agents often encounter partial observability, where incomplete or noisy information obscures the true state of the environment. Partially Observable Markov Decision Processes (POMDPs) are commonly used to model these environments, but effective performance requires memory mechanisms to utilise past observations. While recurrence networks have traditionally addressed this need, transformer-based models have recently shown improved sample efficiency in RL tasks. However, their application to POMDPs remains underdeveloped, and their real-world deployment is constrained due to the high parameter count. This work introduces a novel bi-recurrent model architecture that improves sample efficiency and reduces model parameter count in POMDP scenarios. The architecture replaces the multiple feed forward layers with a single layer of bi-directional recurrence unit to better capture and utilize sequential dependencies and contextual information. This approach improves the model's ability to handle partial observability and increases sample efficiency, enabling effective learning from comparatively fewer interactions. To evaluate the performance of the proposed model architecture, experiments were conducted on a total of 23 POMDP environments. The proposed model architecture outperforms existing transformer-based, attention-based, and recurrence-based methods by a margin ranging from 87.39% to 482.04% on average across the 23 POMDP environments.

Related papers

• Reinforced Model Merging [53.84354455400038]
  We present an innovative framework termed Reinforced Model Merging (RMM), which encompasses an environment and agent tailored for merging tasks.<n>By utilizing data subsets during the evaluation process, we addressed the bottleneck in the reward feedback phase, thereby accelerating RMM by up to 100 times.
  arXiv  Detail & Related papers  (2025-03-27T08:52:41Z)
• Distilling Reinforcement Learning Algorithms for In-Context Model-Based Planning [39.53836535326121]
  We propose Distillation for In-Context Planning (DICP), an in-context model-based RL framework where Transformers simultaneously learn environment dynamics and improve policy in-context.<n>Our results show that DICP achieves state-of-the-art performance while requiring significantly fewer environment interactions than baselines.
  arXiv  Detail & Related papers  (2025-02-26T10:16:57Z)
• ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts [71.91042186338163]
  ALoRE is a novel PETL method that reuses the hypercomplex parameterized space constructed by Kronecker product to Aggregate Low Rank Experts.<n>Thanks to the artful design, ALoRE maintains negligible extra parameters and can be effortlessly merged into the frozen backbone.
  arXiv  Detail & Related papers  (2024-12-11T12:31:30Z)
• POMONAG: Pareto-Optimal Many-Objective Neural Architecture Generator [4.09225917049674]
  Transferable NAS has emerged, generalizing the search process from dataset-dependent to task-dependent. This paper introduces POMONAG, extending DiffusionNAG via a many-optimal diffusion process. Results were validated on two search spaces -- NAS201 and MobileNetV3 -- and evaluated across 15 image classification datasets.
  arXiv  Detail & Related papers  (2024-09-30T16:05:29Z)
• DPPA: Pruning Method for Large Language Model to Model Merging [39.13317231533299]
  We introduce a dual-stage method termed Dynamic Pruning Partition Amplification (DPPA) to tackle the challenge of merging complex fine-tuned models. We show that our method maintains a mere 20% of domain-specific parameters and yet delivers a performance comparable to other methodologies. Our method displays outstanding performance post-pruning, leading to a significant improvement of nearly 20% performance in model merging.
  arXiv  Detail & Related papers  (2024-03-05T09:12:49Z)
• Sample Complexity Characterization for Linear Contextual MDPs [67.79455646673762]
  Contextual decision processes (CMDPs) describe a class of reinforcement learning problems in which the transition kernels and reward functions can change over time with different MDPs indexed by a context variable. CMDPs serve as an important framework to model many real-world applications with time-varying environments. We study CMDPs under two linear function approximation models: Model I with context-varying representations and common linear weights for all contexts; and Model II with common representations for all contexts and context-varying linear weights.
  arXiv  Detail & Related papers  (2024-02-05T03:25:04Z)
• Consensus-Adaptive RANSAC [104.87576373187426]
  We propose a new RANSAC framework that learns to explore the parameter space by considering the residuals seen so far via a novel attention layer. The attention mechanism operates on a batch of point-to-model residuals, and updates a per-point estimation state to take into account the consensus found through a lightweight one-step transformer.
  arXiv  Detail & Related papers  (2023-07-26T08:25:46Z)
• Optimizing Hyperparameters with Conformal Quantile Regression [7.316604052864345]
  We propose to leverage conformalized quantile regression which makes minimal assumptions about the observation noise. This translates to quicker HPO convergence on empirical benchmarks.
  arXiv  Detail & Related papers  (2023-05-05T15:33:39Z)
• Latent Variable Representation for Reinforcement Learning [131.03944557979725]
  It remains unclear theoretically and empirically how latent variable models may facilitate learning, planning, and exploration to improve the sample efficiency of model-based reinforcement learning. We provide a representation view of the latent variable models for state-action value functions, which allows both tractable variational learning algorithm and effective implementation of the optimism/pessimism principle. In particular, we propose a computationally efficient planning algorithm with UCB exploration by incorporating kernel embeddings of latent variable models.
  arXiv  Detail & Related papers  (2022-12-17T00:26:31Z)
• Learning Robust State Abstractions for Hidden-Parameter Block MDPs [55.31018404591743]
  We leverage ideas of common structure from the HiP-MDP setting to enable robust state abstractions inspired by Block MDPs. We derive instantiations of this new framework for both multi-task reinforcement learning (MTRL) and meta-reinforcement learning (Meta-RL) settings.
  arXiv  Detail & Related papers  (2020-07-14T17:25:27Z)

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.