Open-World Reinforcement Learning over Long Short-Term Imagination

• URL: http://arxiv.org/abs/2410.03618v1
• Date: Fri, 4 Oct 2024 17:17:30 GMT
• Title: Open-World Reinforcement Learning over Long Short-Term Imagination
• Authors: Jiajian Li, Qi Wang, Yunbo Wang, Xin Jin, Yang Li, Wenjun Zeng, Xiaokang Yang,
• Abstract summary: We present LS-Imagine, which extends the imagination horizon within a limited number of state transition steps. Our method demonstrates significant improvements over state-of-the-art techniques in MineDojo.
• Score: 91.28998327423295
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Training visual reinforcement learning agents in a high-dimensional open world presents significant challenges. While various model-based methods have improved sample efficiency by learning interactive world models, these agents tend to be "short-sighted", as they are typically trained on short snippets of imagined experiences. We argue that the primary obstacle in open-world decision-making is improving the efficiency of off-policy exploration across an extensive state space. In this paper, we present LS-Imagine, which extends the imagination horizon within a limited number of state transition steps, enabling the agent to explore behaviors that potentially lead to promising long-term feedback. The foundation of our approach is to build a long short-term world model. To achieve this, we simulate goal-conditioned jumpy state transitions and compute corresponding affordance maps by zooming in on specific areas within single images. This facilitates the integration of direct long-term values into behavior learning. Our method demonstrates significant improvements over state-of-the-art techniques in MineDojo.

Related papers

• Learning World Models for Unconstrained Goal Navigation [4.549550797148707]
  We introduce a goal-directed exploration algorithm, MUN, for learning world models. MUN is capable of modeling state transitions between arbitrary subgoal states in the replay buffer. Results demonstrate that MUN strengthens the reliability of world models and significantly improves the policy's capacity to generalize.
  arXiv  Detail & Related papers  (2024-11-03T01:35:06Z)
• ReCoRe: Regularized Contrastive Representation Learning of World Model [21.29132219042405]
  We present a world model that learns invariant features using contrastive unsupervised learning and an intervention-invariant regularizer. Our method outperforms current state-of-the-art model-based and model-free RL methods and significantly improves on out-of-distribution point navigation tasks evaluated on the iGibson benchmark.
  arXiv  Detail & Related papers  (2023-12-14T15:53:07Z)
• Hieros: Hierarchical Imagination on Structured State Space Sequence World Models [4.922995343278039]
  Hieros is a hierarchical policy that learns time abstracted world representations and imagines trajectories at multiple time scales in latent space. We show that our approach outperforms the state of the art in terms of mean and median normalized human score on the Atari 100k benchmark.
  arXiv  Detail & Related papers  (2023-10-08T13:52:40Z)
• Generalizing Event-Based Motion Deblurring in Real-World Scenarios [62.995994797897424]
  Event-based motion deblurring has shown promising results by exploiting low-latency events. We propose a scale-aware network that allows flexible input spatial scales and enables learning from different temporal scales of motion blur. A two-stage self-supervised learning scheme is then developed to fit real-world data distribution.
  arXiv  Detail & Related papers  (2023-08-11T04:27:29Z)
• Self-supervised novel 2D view synthesis of large-scale scenes with efficient multi-scale voxel carving [77.07589573960436]
  We introduce an efficient multi-scale voxel carving method to generate novel views of real scenes. Our final high-resolution output is efficiently self-trained on data automatically generated by the voxel carving module. We demonstrate the effectiveness of our method on highly complex and large-scale scenes in real environments.
  arXiv  Detail & Related papers  (2023-06-26T13:57:05Z)
• DALG: Deep Attentive Local and Global Modeling for Image Retrieval [26.773211032906854]
  We propose a fully attention based framework for robust representation learning motivated by the success of Transformer. Besides applying Transformer for global feature extraction, we devise a local branch composed of window-based multi-head attention and spatial attention. With our Deep Attentive Local and Global modeling framework (DALG), extensive experimental results show that efficiency can be significantly improved.
  arXiv  Detail & Related papers  (2022-07-01T09:32:15Z)
• Model-Based Reinforcement Learning via Latent-Space Collocation [110.04005442935828]
  We argue that it is easier to solve long-horizon tasks by planning sequences of states rather than just actions. We adapt the idea of collocation, which has shown good results on long-horizon tasks in optimal control literature, to the image-based setting by utilizing learned latent state space models.
  arXiv  Detail & Related papers  (2021-06-24T17:59:18Z)
• Bridging Imagination and Reality for Model-Based Deep Reinforcement Learning [72.18725551199842]
  We propose a novel model-based reinforcement learning algorithm, called BrIdging Reality and Dream (BIRD) It maximizes the mutual information between imaginary and real trajectories so that the policy improvement learned from imaginary trajectories can be easily generalized to real trajectories. We demonstrate that our approach improves sample efficiency of model-based planning, and achieves state-of-the-art performance on challenging visual control benchmarks.
  arXiv  Detail & Related papers  (2020-10-23T03:22:01Z)
• Learning Long-term Visual Dynamics with Region Proposal Interaction Networks [75.06423516419862]
  We build object representations that can capture inter-object and object-environment interactions over a long-range. Thanks to the simple yet effective object representation, our approach outperforms prior methods by a significant margin.
  arXiv  Detail & Related papers  (2020-08-05T17:48:00Z)

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.