Graph augmented Deep Reinforcement Learning in the GameRLand3D environment

• URL: http://arxiv.org/abs/2112.11731v1
• Date: Wed, 22 Dec 2021 08:48:00 GMT
• Title: Graph augmented Deep Reinforcement Learning in the GameRLand3D environment
• Authors: Edward Beeching, Maxim Peter, Philippe Marcotte, Jilles Debangoye, Olivier Simonin, Joshua Romoff, Christian Wolf
• Abstract summary: We introduce a hybrid technique combining a low level policy trained with reinforcement learning and a graph based high level classical planner. In an in-depth experimental study, we quantify the limitations of end-to-end Deep RL approaches in vast environments. We also introduce "GameRLand3D", a new benchmark and soon to be released environment can generate complex procedural 3D maps for navigation tasks.
• Score: 11.03710870581386
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We address planning and navigation in challenging 3D video games featuring maps with disconnected regions reachable by agents using special actions. In this setting, classical symbolic planners are not applicable or difficult to adapt. We introduce a hybrid technique combining a low level policy trained with reinforcement learning and a graph based high level classical planner. In addition to providing human-interpretable paths, the approach improves the generalization performance of an end-to-end approach in unseen maps, where it achieves a 20% absolute increase in success rate over a recurrent end-to-end agent on a point to point navigation task in yet unseen large-scale maps of size 1km x 1km. In an in-depth experimental study, we quantify the limitations of end-to-end Deep RL approaches in vast environments and we also introduce "GameRLand3D", a new benchmark and soon to be released environment can generate complex procedural 3D maps for navigation tasks.

Related papers

• Versatile Navigation under Partial Observability via Value-guided Diffusion Policy [14.967107015417943]
  We propose a versatile diffusion-based approach for both 2D and 3D route planning under partial observability. Specifically, our value-guided diffusion policy first generates plans to predict actions across various timesteps. We then employ a differentiable planner with state estimations to derive a value function, directing the agent's exploration and goal-seeking behaviors.
  arXiv  Detail & Related papers  (2024-04-01T19:52:08Z)
• Deep Reinforcement Learning with Dynamic Graphs for Adaptive Informative Path Planning [22.48658555542736]
  Key task in robotic data acquisition is planning paths through an initially unknown environment to collect observations. We propose a novel deep reinforcement learning approach for adaptively replanning robot paths to map targets of interest in unknown 3D environments.
  arXiv  Detail & Related papers  (2024-02-07T14:24:41Z)
• How To Not Train Your Dragon: Training-free Embodied Object Goal Navigation with Semantic Frontiers [94.46825166907831]
  We present a training-free solution to tackle the object goal navigation problem in Embodied AI. Our method builds a structured scene representation based on the classic visual simultaneous localization and mapping (V-SLAM) framework. Our method propagates semantics on the scene graphs based on language priors and scene statistics to introduce semantic knowledge to the geometric frontiers.
  arXiv  Detail & Related papers  (2023-05-26T13:38:33Z)
• GraphCSPN: Geometry-Aware Depth Completion via Dynamic GCNs [49.55919802779889]
  We propose a Graph Convolution based Spatial Propagation Network (GraphCSPN) as a general approach for depth completion. In this work, we leverage convolution neural networks as well as graph neural networks in a complementary way for geometric representation learning. Our method achieves the state-of-the-art performance, especially when compared in the case of using only a few propagation steps.
  arXiv  Detail & Related papers  (2022-10-19T17:56:03Z)
• Bridging the Gap Between Learning in Discrete and Continuous Environments for Vision-and-Language Navigation [41.334731014665316]
  Most existing works in vision-and-language navigation (VLN) focus on either discrete or continuous environments. We propose a predictor to generate a set of candidate waypoints during navigation. We show that agents navigating in continuous environments with predicted waypoints perform significantly better than agents using low-level actions.
  arXiv  Detail & Related papers  (2022-03-05T14:56:14Z)
• ViKiNG: Vision-Based Kilometer-Scale Navigation with Geographic Hints [94.60414567852536]
  Long-range navigation requires both planning and reasoning about local traversability. We propose a learning-based approach that integrates learning and planning. ViKiNG can leverage its image-based learned controller and goal-directed to navigate to goals up to 3 kilometers away.
  arXiv  Detail & Related papers  (2022-02-23T02:14:23Z)
• Landmark Policy Optimization for Object Navigation Task [77.34726150561087]
  This work studies object goal navigation task, which involves navigating to the closest object related to the given semantic category in unseen environments. Recent works have shown significant achievements both in the end-to-end Reinforcement Learning approach and modular systems, but need a big step forward to be robust and optimal. We propose a hierarchical method that incorporates standard task formulation and additional area knowledge as landmarks, with a way to extract these landmarks.
  arXiv  Detail & Related papers  (2021-09-17T12:28:46Z)
• Hierarchical Robot Navigation in Novel Environments using Rough 2-D Maps [21.245942227850733]
  We propose an approach that leverages a rough 2-D map of the environment to navigate in novel environments without requiring further learning. Because the low-level controller is only trained with local behaviors, this framework allows us to generalize to novel environments. Experimental results demonstrate the effectiveness of the proposed framework in both seen and novel environments.
  arXiv  Detail & Related papers  (2021-06-07T14:42:51Z)
• Occupancy Anticipation for Efficient Exploration and Navigation [97.17517060585875]
  We propose occupancy anticipation, where the agent uses its egocentric RGB-D observations to infer the occupancy state beyond the visible regions. By exploiting context in both the egocentric views and top-down maps our model successfully anticipates a broader map of the environment. Our approach is the winning entry in the 2020 Habitat PointNav Challenge.
  arXiv  Detail & Related papers  (2020-08-21T03:16:51Z)
• Improving Target-driven Visual Navigation with Attention on 3D Spatial Relationships [52.72020203771489]
  We investigate target-driven visual navigation using deep reinforcement learning (DRL) in 3D indoor scenes. Our proposed method combines visual features and 3D spatial representations to learn navigation policy. Our experiments, performed in the AI2-THOR, show that our model outperforms the baselines in both SR and SPL metrics.
  arXiv  Detail & Related papers  (2020-04-29T08:46:38Z)

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.