We study how to transfer representations pretrained on source tasks to target tasks in visual percept based RL. We analyze two popular approaches: freezing or finetuning the pretrained representations. Empirical studies on a set of popular tasks reveal several properties of pretrained representations. First, finetuning is required even when pretrained representations perfectly capture the information required to solve the target task. Second, finetuned representations improve learnability and are more robust to noise. Third, pretrained bottom layers are task-agnostic and readily transferable to new tasks, while top layers encode task-specific information and require adaptation. Building on these insights, we propose a self-supervised objective that clusters representations according to the policy they induce, as opposed to traditional representation similarity measures which are policy-agnostic (e.g. Euclidean norm, cosine similarity). Together with freezing the bottom layers, this objective results in significantly better representation than frozen, finetuned, and self-supervised alternatives on a wide range of benchmarks.
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Salesforce Research（Salesforce研究院）
Recent theoretical work studies sample-efficient reinforcement learning (RL) extensively in two settings: learning interactively in the environment (online RL), or learning from an offline dataset (offline RL). However, existing algorithms and theories for learning near-optimal policies in these two settings are rather different and disconnected. Towards bridging this gap, this paper initiates the theoretical study of policy finetuning, that is, online RL where the learner has additional access to a "reference policy" $μ$ close to the optimal policy $π_\star$ in a certain sense. We consider th…
Offline reinforcement learning (RL) allows for the training of competent agents from offline datasets without any interaction with the environment. Online finetuning of such offline models can further improve performance. But how should we ideally finetune agents obtained from offline RL training? While offline RL algorithms can in principle be used for finetuning, in practice, their online performance improves slowly. In contrast, we show that it is possible to use standard online off-policy algorithms for faster improvement. However, we find this approach may suffer from policy collapse, whe…
Cinnamon AI（肉桂人工智能公司）；Hung Yen University of Technology and Education（兴安技术教育大学）；Deakin University（迪肯大学）
Successful Artificial Intelligence systems often require numerous labeled data to extract information from document images. In this paper, we investigate the problem of improving the performance of Artificial Intelligence systems in understanding document images, especially in cases where training data is limited. We address the problem by proposing a novel finetuning method using reinforcement learning. Our approach treats the Information Extraction model as a policy network and uses policy gradient training to update the model to maximize combined reward functions that complement the traditi…
Towards Fast Safe Online Reinforcement Learning via Policy Finetuning
School of Electrical, Computer and Energy Engineering（电气、计算机与能源工程学院）；Arizona State University（亚利桑那州立大学）；School of Electrical Engineering and Computer Science（电气工程与计算机科学学院）；Washington State University（华盛顿州立大学）；Department of Computer Science（计算机科学系）；University of Houston（休斯顿大学）
Learning-based methods in robotics hold the promise of generalization, but what can be done if a learned policy does not generalize to a new situation? In principle, if an agent can at least evaluate its own success (i.e., with a reward classifier that generalizes well even when the policy does not), it could actively practice the task and finetune the policy in this situation. We study this problem in the setting of industrial insertion tasks, such as inserting connectors in sockets and setting screws. Existing algorithms rely on precise localization of the connector or socket and carefully m…
University of Toronto（多伦多大学）；Vector Institute（矢量研究所）；Northwestern University（西北大学）；UC Santa Cruz（加州大学圣克鲁兹分校）
Most existing policy learning solutions require the learning agents to receive high-quality supervision signals such as well-designed rewards in reinforcement learning (RL) or high-quality expert demonstrations in behavioral cloning (BC). These quality supervisions are usually infeasible or prohibitively expensive to obtain in practice. We aim for a unified framework that leverages the available cheap weak supervisions to perform policy learning efficiently. To handle this problem, we treat the "weak supervision" as imperfect information coming from a peer agent, and evaluate the learning agen…
Coherent Off-Policy Improvement of Large Behavior Models with Learned Rewards
Technical University of Darmstadt（达姆施塔特技术大学）；University of Oxford（牛津大学）；Zuse School ELIZA（泽努斯学校ELIZA）；hessian.AI（海西斯AI）；German Research Center for AI (DFKI)（德国人工智能研究中心（DFKI））；Robotics Institute Germany (RIG)（德国机器人研究所）
Supervised regression to demonstrations has been demonstrated to be a stable way to train deep policy networks. We are motivated to study how we can take full advantage of supervised loss functions for stably training deep reinforcement learning agents. This is a challenging task because it is unclear how the training data could be collected to enable policy improvement. In this work, we propose Self-Supervised Reinforcement Learning (SSRL), a simple algorithm that optimizes policies with purely supervised losses. We demonstrate that, without policy gradient or value estimation, an iterative p…
Detailed routing is one of the most critical steps in analog circuit design. Complete routing has become increasingly more challenging in advanced node analog circuits, making advances in efficient automatic routers ever more necessary. In this work, we propose a machine learning driven method for solving the track-assignment detailed routing problem for advanced node analog circuits. Our approach adopts an attention-based reinforcement learning (RL) policy model. Our main insight and advancement over this RL model is the use of supervision as a way to leverage solutions generated by a convent…
This paper addresses the question of how a previously available control policy $π_s$ can be used as a supervisor to more quickly and safely train a new learned control policy $π_L$ for a robot. A weighted average of the supervisor and learned policies is used during trials, with a heavier weight initially on the supervisor, in order to allow safe and useful physical trials while the learned policy is still ineffective. During the process, the weight is adjusted to favor the learned policy. As weights are adjusted, the learned network must compensate so as to give safe and reasonable outputs un…
Georgia Institute of Technology（佐治亚理工学院）；FAIR, Meta AI（Meta人工智能研究院（FAIR））
We study ObjectGoal Navigation -- where a virtual robot situated in a new environment is asked to navigate to an object. Prior work has shown that imitation learning (IL) using behavior cloning (BC) on a dataset of human demonstrations achieves promising results. However, this has limitations -- 1) BC policies generalize poorly to new states, since the training mimics actions not their consequences, and 2) collecting demonstrations is expensive. On the other hand, reinforcement learning (RL) is trivially scalable, but requires careful reward engineering to achieve desirable behavior. We presen…
Policy and World Modeling Co-Training for Language Agents
Southern University of Science and Technology（南方科技大学）；Hong Kong University of Science and Technology（香港科学大学）；Hong Kong University of Science and Technology (Guangzhou)（香港科学大学（广州））；Hong Kong Polytechnic University（香港理工大学）；LIGHTSPEED
Videos are Sample-Efficient Supervisions: Behavior Cloning from Videos via Latent Representations
State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences（多模态人工智能系统国家重点实验室，自动化研究所，中国科学院）；School of Artificial Intelligence, University of Chinese Academy of Sciences（人工智能学院，中国科学院大学）
Teacher-Guided Policy Optimization for On-Policy Reasoning Distillation under Large Policy Divergence
School of Computer Science and Engineering, Northeastern University, China（东北大学计算机科学与工程学院）；Tsinghua University（清华大学）；Meituan（美团）；Meta AI；NiuTrans Research, Shenyang, China（新译研究院，沈阳，中国）
SCOPE: Signal-Calibrated On-Policy Distillation Enhancement with Dual-Path Adaptive Weighting
University of Science and Technology of China（中国科学技术大学）；Meituan LongCat Interaction Team（美团 LongCat 交互团队）；Nanjing University（南京大学）；Fudan University（复旦大学）；Huazhong University of Science and Technology（华中科技大学）
Anticipating price developments in financial markets is a topic of continued interest in forecasting. Funneled by advancements in deep learning and natural language processing (NLP) together with the availability of vast amounts of textual data in form of news articles, social media postings, etc., an increasing number of studies incorporate text-based predictors in forecasting models. We contribute to this literature by introducing weak learning, a recently proposed NLP approach to address the problem that text data is unlabeled. Without a dependent variable, it is not possible to finetune pr…
