Hierarchical Reinforcement Learning in Complex 3D Environments

• URL: http://arxiv.org/abs/2302.14451v1
• Date: Tue, 28 Feb 2023 09:56:36 GMT
• Title: Hierarchical Reinforcement Learning in Complex 3D Environments
• Authors: Bernardo Avila Pires, Feryal Behbahani, Hubert Soyer, Kyriacos Nikiforou, Thomas Keck, Satinder Singh
• Abstract summary: Hierarchical Reinforcement Learning (HRL) agents have the potential to demonstrate appealing capabilities. Recent successes with HRL across different domains provide evidence that practical, effective HRL agents are possible. Despite these successes, visually complex partially observable 3D environments remained a challenge for HRL agents.
• Score: 16.16652618709808
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Hierarchical Reinforcement Learning (HRL) agents have the potential to demonstrate appealing capabilities such as planning and exploration with abstraction, transfer, and skill reuse. Recent successes with HRL across different domains provide evidence that practical, effective HRL agents are possible, even if existing agents do not yet fully realize the potential of HRL. Despite these successes, visually complex partially observable 3D environments remained a challenge for HRL agents. We address this issue with Hierarchical Hybrid Offline-Online (H2O2), a hierarchical deep reinforcement learning agent that discovers and learns to use options from scratch using its own experience. We show that H2O2 is competitive with a strong non-hierarchical Muesli baseline in the DeepMind Hard Eight tasks and we shed new light on the problem of learning hierarchical agents in complex environments. Our empirical study of H2O2 reveals previously unnoticed practical challenges and brings new perspective to the current understanding of hierarchical agents in complex domains.

Related papers

• Meta-Learning Integration in Hierarchical Reinforcement Learning for Advanced Task Complexity [0.0]
  Hierarchical Reinforcement Learning (HRL) effectively tackles complex tasks by decomposing them into structured policies. We integrate meta-learning into HRL to enhance the agent's ability to learn and adapt hierarchical policies swiftly.
  arXiv  Detail & Related papers  (2024-10-10T13:47:37Z)
• Imagination-Augmented Hierarchical Reinforcement Learning for Safe and Interactive Autonomous Driving in Urban Environments [21.30432408940134]
  Hierarchical reinforcement learning (HRL) incorporates temporal abstraction into reinforcement learning (RL) We propose imagination-augmented HRL (IAHRL) that efficiently integrates imagination into HRL. IAHRL enables an agent to perform safe and interactive behaviors, achieving higher success rates and lower average episode steps than baselines.
  arXiv  Detail & Related papers  (2023-11-17T03:41:22Z)
• METRA: Scalable Unsupervised RL with Metric-Aware Abstraction [69.90741082762646]
  Metric-Aware Abstraction (METRA) is a novel unsupervised reinforcement learning objective. By learning to move in every direction in the latent space, METRA obtains a tractable set of diverse behaviors. We show that METRA can discover a variety of useful behaviors even in complex, pixel-based environments.
  arXiv  Detail & Related papers  (2023-10-13T06:43:11Z)
• Human-Timescale Adaptation in an Open-Ended Task Space [56.55530165036327]
  We show that training an RL agent at scale leads to a general in-context learning algorithm that can adapt to open-ended novel embodied 3D problems as quickly as humans. Our results lay the foundation for increasingly general and adaptive RL agents that perform well across ever-larger open-ended domains.
  arXiv  Detail & Related papers  (2023-01-18T15:39:21Z)
• A Survey on Explainable Reinforcement Learning: Concepts, Algorithms, Challenges [38.70863329476517]
  Reinforcement Learning (RL) is a popular machine learning paradigm where intelligent agents interact with the environment to fulfill a long-term goal. Despite the encouraging results achieved, the deep neural network-based backbone is widely deemed as a black box that impedes practitioners to trust and employ trained agents in realistic scenarios where high security and reliability are essential. To alleviate this issue, a large volume of literature devoted to shedding light on the inner workings of the intelligent agents has been proposed, by constructing intrinsic interpretability or post-hoc explainability.
  arXiv  Detail & Related papers  (2022-11-12T13:52:06Z)
• Causality-driven Hierarchical Structure Discovery for Reinforcement Learning [36.03953383550469]
  We propose CDHRL, a causality-driven hierarchical reinforcement learning framework. We show that CDHRL significantly boosts exploration efficiency with the causality-driven paradigm. The results in two complex environments, 2D-Minecraft and Eden, show that CDHRL significantly boosts exploration efficiency with the causality-driven paradigm.
  arXiv  Detail & Related papers  (2022-10-13T12:42:48Z)
• URLB: Unsupervised Reinforcement Learning Benchmark [82.36060735454647]
  We introduce the Unsupervised Reinforcement Learning Benchmark (URLB) URLB consists of two phases: reward-free pre-training and downstream task adaptation with extrinsic rewards. We provide twelve continuous control tasks from three domains for evaluation and open-source code for eight leading unsupervised RL methods.
  arXiv  Detail & Related papers  (2021-10-28T15:07:01Z)
• Provable Hierarchy-Based Meta-Reinforcement Learning [50.17896588738377]
  We analyze HRL in the meta-RL setting, where learner learns latent hierarchical structure during meta-training for use in a downstream task. We provide "diversity conditions" which, together with a tractable optimism-based algorithm, guarantee sample-efficient recovery of this natural hierarchy. Our bounds incorporate common notions in HRL literature such as temporal and state/action abstractions, suggesting that our setting and analysis capture important features of HRL in practice.
  arXiv  Detail & Related papers  (2021-10-18T17:56:02Z)
• Explore and Control with Adversarial Surprise [78.41972292110967]
  Reinforcement learning (RL) provides a framework for learning goal-directed policies given user-specified rewards. We propose a new unsupervised RL technique based on an adversarial game which pits two policies against each other to compete over the amount of surprise an RL agent experiences. We show that our method leads to the emergence of complex skills by exhibiting clear phase transitions.
  arXiv  Detail & Related papers  (2021-07-12T17:58:40Z)
• Forgetful Experience Replay in Hierarchical Reinforcement Learning from Demonstrations [55.41644538483948]
  In this paper, we propose a combination of approaches that allow the agent to use low-quality demonstrations in complex vision-based environments. Our proposed goal-oriented structuring of replay buffer allows the agent to automatically highlight sub-goals for solving complex hierarchical tasks in demonstrations. The solution based on our algorithm beats all the solutions for the famous MineRL competition and allows the agent to mine a diamond in the Minecraft environment.
  arXiv  Detail & Related papers  (2020-06-17T15:38:40Z)

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.