Importance Sampling-Guided Meta-Training for Intelligent Agents in Highly Interactive Environments

• URL: http://arxiv.org/abs/2407.15839v2
• Date: Mon, 28 Oct 2024 04:48:53 GMT
• Title: Importance Sampling-Guided Meta-Training for Intelligent Agents in Highly Interactive Environments
• Authors: Mansur Arief, Mike Timmerman, Jiachen Li, David Isele, Mykel J Kochenderfer,
• Abstract summary: This study introduces a novel training framework that integrates guided meta RL with importance sampling (IS) to optimize training distributions. By estimating a naturalistic distribution from real-world datasets, the framework ensures a balanced focus across common and extreme driving scenarios.
• Score: 43.144056801987595
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Training intelligent agents to navigate highly interactive environments presents significant challenges. While guided meta reinforcement learning (RL) approach that first trains a guiding policy to train the ego agent has proven effective in improving generalizability across scenarios with various levels of interaction, the state-of-the-art method tends to be overly sensitive to extreme cases, impairing the agents' performance in the more common scenarios. This study introduces a novel training framework that integrates guided meta RL with importance sampling (IS) to optimize training distributions iteratively for navigating highly interactive driving scenarios, such as T-intersections or roundabouts. Unlike traditional methods that may underrepresent critical interactions or overemphasize extreme cases during training, our approach strategically adjusts the training distribution towards more challenging driving behaviors using IS proposal distributions and applies the importance ratio to de-bias the result. By estimating a naturalistic distribution from real-world datasets and employing a mixture model for iterative training refinements, the framework ensures a balanced focus across common and extreme driving scenarios. Experiments conducted with both synthetic and naturalistic datasets demonstrate both accelerated training and performance improvements under highly interactive driving tasks.

Related papers

• Enabling Adaptive Agent Training in Open-Ended Simulators by Targeting Diversity [10.402855891273346]
  DIVA is an evolutionary approach for generating diverse training tasks in complex, open-ended simulators. Our empirical results showcase DIVA's unique ability to overcome complex parameterizations and successfully train adaptive agent behavior.
  arXiv  Detail & Related papers  (2024-11-07T06:27:12Z)
• Analyzing Closed-loop Training Techniques for Realistic Traffic Agent Models in Autonomous Highway Driving Simulations [4.486517725808305]
  We provide an extensive comparative analysis of different training principles, with a focus on closed-loop methods for highway driving simulation. We experimentally compare (i) open-loop vs. closed-loop multi-agent training, (ii) adversarial vs. deterministic supervised training, (iii) the impact of reinforcement losses, and (iv) the impact of training alongside log-replayed agents to identify suitable training techniques for realistic agent modeling.
  arXiv  Detail & Related papers  (2024-10-21T13:16:58Z)
• Learning to Model Diverse Driving Behaviors in Highly Interactive Autonomous Driving Scenarios with Multi-Agent Reinforcement Learning [0.751422531359304]
  Multi-Agent Reinforcement Learning (MARL) has shown impressive results in many driving scenarios. However, the performance of these trained policies can be impacted when faced with diverse driving styles and personalities. We introduce the Personality Modeling Network (PeMN), which includes a cooperation value function and personality parameters.
  arXiv  Detail & Related papers  (2024-02-21T02:44:33Z)
• Interactive Autonomous Navigation with Internal State Inference and Interactivity Estimation [58.21683603243387]
  We propose three auxiliary tasks with relational-temporal reasoning and integrate them into the standard Deep Learning framework. These auxiliary tasks provide additional supervision signals to infer the behavior patterns other interactive agents. Our approach achieves robust and state-of-the-art performance in terms of standard evaluation metrics.
  arXiv  Detail & Related papers  (2023-11-27T18:57:42Z)
• Multi-Agent Reinforcement Learning-Based UAV Pathfinding for Obstacle Avoidance in Stochastic Environment [12.122881147337505]
  We propose a novel centralized training with decentralized execution method based on multi-agent reinforcement learning. In our approach, agents communicate only with the centralized planner to make decentralized decisions online. We conduct multi-step value convergence in multi-agent reinforcement learning to enhance the training efficiency.
  arXiv  Detail & Related papers  (2023-10-25T14:21:22Z)
• ALP: Action-Aware Embodied Learning for Perception [60.64801970249279]
  We introduce Action-Aware Embodied Learning for Perception (ALP) ALP incorporates action information into representation learning through a combination of optimizing a reinforcement learning policy and an inverse dynamics prediction objective. We show that ALP outperforms existing baselines in several downstream perception tasks.
  arXiv  Detail & Related papers  (2023-06-16T21:51:04Z)
• Value Function is All You Need: A Unified Learning Framework for Ride Hailing Platforms [57.21078336887961]
  Large ride-hailing platforms, such as DiDi, Uber and Lyft, connect tens of thousands of vehicles in a city to millions of ride demands throughout the day. We propose a unified value-based dynamic learning framework (V1D3) for tackling both tasks.
  arXiv  Detail & Related papers  (2021-05-18T19:22:24Z)
• Language-guided Navigation via Cross-Modal Grounding and Alternate Adversarial Learning [66.9937776799536]
  The emerging vision-and-language navigation (VLN) problem aims at learning to navigate an agent to the target location in unseen photo-realistic environments. The main challenges of VLN arise mainly from two aspects: first, the agent needs to attend to the meaningful paragraphs of the language instruction corresponding to the dynamically-varying visual environments. We propose a cross-modal grounding module to equip the agent with a better ability to track the correspondence between the textual and visual modalities.
  arXiv  Detail & Related papers  (2020-11-22T09:13:46Z)
• Dynamics Generalization via Information Bottleneck in Deep Reinforcement Learning [90.93035276307239]
  We propose an information theoretic regularization objective and an annealing-based optimization method to achieve better generalization ability in RL agents. We demonstrate the extreme generalization benefits of our approach in different domains ranging from maze navigation to robotic tasks. This work provides a principled way to improve generalization in RL by gradually removing information that is redundant for task-solving.
  arXiv  Detail & Related papers  (2020-08-03T02:24:20Z)
• MAPPER: Multi-Agent Path Planning with Evolutionary Reinforcement Learning in Mixed Dynamic Environments [30.407700996710023]
  This paper proposes a decentralized partially observable multi-agent path planning with evolutionary reinforcement learning (MAPPER) method. We decompose the long-range navigation task into many easier sub-tasks under the guidance of a global planner. Our approach models dynamic obstacles' behavior with an image-based representation and trains a policy in mixed dynamic environments without homogeneity assumption.
  arXiv  Detail & Related papers  (2020-07-30T20:14:42Z)

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.