Scaling Offline Model-Based RL via Jointly-Optimized World-Action Model Pretraining

• URL: http://arxiv.org/abs/2410.00564v2
• Date: Tue, 8 Oct 2024 13:41:43 GMT
• Title: Scaling Offline Model-Based RL via Jointly-Optimized World-Action Model Pretraining
• Authors: Jie Cheng, Ruixi Qiao, Gang Xiong, Qinghai Miao, Yingwei Ma, Binhua Li, Yongbin Li, Yisheng Lv,
• Abstract summary: We introduce JOWA: Jointly-Reinforced World-Action model, an offline model-based RL agent pretrained on Atari games with 6 billion tokens data. Our largest agent, with 150 million parameters, 78.9% human-level performance on pretrained games using only 10% subsampled offline data, outperforming existing state-of-the-art large-scale offline RL baselines by 31.6% on averange.
• Score: 49.730897226510095
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: A significant aspiration of offline reinforcement learning (RL) is to develop a generalist agent with high capabilities from large and heterogeneous datasets. However, prior approaches that scale offline RL either rely heavily on expert trajectories or struggle to generalize to diverse unseen tasks. Inspired by the excellent generalization of world model in conditional video generation, we explore the potential of image observation-based world model for scaling offline RL and enhancing generalization on novel tasks. In this paper, we introduce JOWA: Jointly-Optimized World-Action model, an offline model-based RL agent pretrained on multiple Atari games with 6 billion tokens data to learn general-purpose representation and decision-making ability. Our method jointly optimizes a world-action model through a shared transformer backbone, which stabilize temporal difference learning with large models during pretraining. Moreover, we propose a provably efficient and parallelizable planning algorithm to compensate for the Q-value estimation error and thus search out better policies. Experimental results indicate that our largest agent, with 150 million parameters, achieves 78.9% human-level performance on pretrained games using only 10% subsampled offline data, outperforming existing state-of-the-art large-scale offline RL baselines by 31.6% on averange. Furthermore, JOWA scales favorably with model capacity and can sample-efficiently transfer to novel games using only 5k offline fine-tuning data (approximately 4 trajectories) per game, demonstrating superior generalization. We will release codes and model weights at https://github.com/CJReinforce/JOWA.

Related papers

• Locality Sensitive Sparse Encoding for Learning World Models Online [29.124825481348285]
  Follow-The-Leader world models are desirable for model-based reinforcement learning. FTL models need re-training on all accumulated data at every interaction step to achieve FTL. We show that our world models learned online using a single pass of trajectory data either surpass or match the performance of deep world models trained with replay.
  arXiv  Detail & Related papers  (2024-01-23T19:00:02Z)
• Reusing Pretrained Models by Multi-linear Operators for Efficient Training [65.64075958382034]
  Training large models from scratch usually costs a substantial amount of resources. Recent studies such as bert2BERT and LiGO have reused small pretrained models to initialize a large model. We propose a method that linearly correlates each weight of the target model to all the weights of the pretrained model.
  arXiv  Detail & Related papers  (2023-10-16T06:16:47Z)
• Offline Q-Learning on Diverse Multi-Task Data Both Scales And Generalizes [100.69714600180895]
  offline Q-learning algorithms exhibit strong performance that scales with model capacity. We train a single policy on 40 games with near-human performance using up-to 80 million parameter networks. Compared to return-conditioned supervised approaches, offline Q-learning scales similarly with model capacity and has better performance, especially when the dataset is suboptimal.
  arXiv  Detail & Related papers  (2022-11-28T08:56:42Z)
• Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels [112.63440666617494]
  Reinforcement learning algorithms can succeed but require large amounts of interactions between the agent and the environment. We propose a new method to solve it, using unsupervised model-based RL, for pre-training the agent. We show robust performance on the Real-Word RL benchmark, hinting at resiliency to environment perturbations during adaptation.
  arXiv  Detail & Related papers  (2022-09-24T14:22:29Z)
• Bootstrapped Transformer for Offline Reinforcement Learning [31.43012728924881]
  offline reinforcement learning (RL) aims at learning policies from previously collected static trajectory data without interacting with the real environment. Recent works provide a novel perspective by viewing offline RL as a generic sequence generation problem. We propose a novel algorithm named Bootstrapped Transformer, which incorporates the idea of bootstrapping and leverages the learned model to self-generate more offline data.
  arXiv  Detail & Related papers  (2022-06-17T05:57:47Z)
• Behavioral Priors and Dynamics Models: Improving Performance and Domain Transfer in Offline RL [82.93243616342275]
  We introduce Offline Model-based RL with Adaptive Behavioral Priors (MABE) MABE is based on the finding that dynamics models, which support within-domain generalization, and behavioral priors, which support cross-domain generalization, are complementary. In experiments that require cross-domain generalization, we find that MABE outperforms prior methods.
  arXiv  Detail & Related papers  (2021-06-16T20:48:49Z)
• Offline Reinforcement Learning from Images with Latent Space Models [60.69745540036375]
  offline reinforcement learning (RL) refers to the problem of learning policies from a static dataset of environment interactions. We build on recent advances in model-based algorithms for offline RL, and extend them to high-dimensional visual observation spaces. Our approach is both tractable in practice and corresponds to maximizing a lower bound of the ELBO in the unknown POMDP.
  arXiv  Detail & Related papers  (2020-12-21T18:28:17Z)

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.