Discovering and Achieving Goals via World Models

• URL: http://arxiv.org/abs/2110.09514v1
• Date: Mon, 18 Oct 2021 17:59:58 GMT
• Title: Discovering and Achieving Goals via World Models
• Authors: Russell Mendonca, Oleh Rybkin, Kostas Daniilidis, Danijar Hafner, Deepak Pathak
• Abstract summary: We introduce Latent Explorer Achiever (LEXA), a unified solution to this problem. LEXA learns a world model from image inputs and uses it to train an explorer and an achiever policy from imagined rollouts. After the unsupervised phase, LEXA solves tasks specified as goal images zero-shot without any additional learning.
• Score: 61.95437238374288
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: How can artificial agents learn to solve many diverse tasks in complex visual environments in the absence of any supervision? We decompose this question into two problems: discovering new goals and learning to reliably achieve them. We introduce Latent Explorer Achiever (LEXA), a unified solution to these that learns a world model from image inputs and uses it to train an explorer and an achiever policy from imagined rollouts. Unlike prior methods that explore by reaching previously visited states, the explorer plans to discover unseen surprising states through foresight, which are then used as diverse targets for the achiever to practice. After the unsupervised phase, LEXA solves tasks specified as goal images zero-shot without any additional learning. LEXA substantially outperforms previous approaches to unsupervised goal-reaching, both on prior benchmarks and on a new challenging benchmark with a total of 40 test tasks spanning across four standard robotic manipulation and locomotion domains. LEXA further achieves goals that require interacting with multiple objects in sequence. Finally, to demonstrate the scalability and generality of LEXA, we train a single general agent across four distinct environments. Code and videos at https://orybkin.github.io/lexa/

Related papers

• Walk the Random Walk: Learning to Discover and Reach Goals Without Supervision [21.72567982148215]
  We propose a novel method for training such a goal-conditioned agent without any external rewards or any domain knowledge. We use random walk to train a reachability network that predicts the similarity between two states. This reachability network is then used in building goal memory containing past observations that are diverse and well-balanced. All the components are kept updated throughout training as the agent discovers and learns new goals.
  arXiv  Detail & Related papers  (2022-06-23T14:29:36Z)
• Deep Hierarchical Planning from Pixels [86.14687388689204]
  Director is a method for learning hierarchical behaviors directly from pixels by planning inside the latent space of a learned world model. Despite operating in latent space, the decisions are interpretable because the world model can decode goals into images for visualization. Director also learns successful behaviors across a wide range of environments, including visual control, Atari games, and DMLab levels.
  arXiv  Detail & Related papers  (2022-06-08T18:20:15Z)
• Zero Experience Required: Plug & Play Modular Transfer Learning for Semantic Visual Navigation [97.17517060585875]
  We present a unified approach to visual navigation using a novel modular transfer learning model. Our model can effectively leverage its experience from one source task and apply it to multiple target tasks. Our approach learns faster, generalizes better, and outperforms SoTA models by a significant margin.
  arXiv  Detail & Related papers  (2022-02-05T00:07:21Z)
• Semantic Tracklets: An Object-Centric Representation for Visual Multi-Agent Reinforcement Learning [126.57680291438128]
  We study whether scalability can be achieved via a disentangled representation. We evaluate semantic tracklets' on the visual multi-agent particle environment (VMPE) and on the challenging visual multi-agent GFootball environment. Notably, this method is the first to successfully learn a strategy for five players in the GFootball environment using only visual data.
  arXiv  Detail & Related papers  (2021-08-06T22:19:09Z)
• GRIMGEP: Learning Progress for Robust Goal Sampling in Visual Deep Reinforcement Learning [21.661530291654692]
  We propose a framework that allows agents to autonomously identify and ignore noisy distracting regions. Our framework can be combined with any state-of-the-art novelty seeking goal exploration approaches.
  arXiv  Detail & Related papers  (2020-08-10T19:50:06Z)
• Automatic Curriculum Learning through Value Disagreement [95.19299356298876]
  Continually solving new, unsolved tasks is the key to learning diverse behaviors. In the multi-task domain, where an agent needs to reach multiple goals, the choice of training goals can largely affect sample efficiency. We propose setting up an automatic curriculum for goals that the agent needs to solve. We evaluate our method across 13 multi-goal robotic tasks and 5 navigation tasks, and demonstrate performance gains over current state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-06-17T03:58:25Z)
• Planning to Explore via Self-Supervised World Models [120.31359262226758]
  Plan2Explore is a self-supervised reinforcement learning agent. We present a new approach to self-supervised exploration and fast adaptation to new tasks. Without any training supervision or task-specific interaction, Plan2Explore outperforms prior self-supervised exploration methods.
  arXiv  Detail & Related papers  (2020-05-12T17:59:45Z)

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.