More Like this

1. Decision Transformers As Zero-Shot Learners via Text-Behavior Alignment

   Zhang, Xin; Martinez, Jonathan; Li, Yanhua; Zhang, Yingzue (April 2026, Forty-third International Conference on Machine Learning)

   Offline meta-reinforcement learning (meta-RL) aims to train agents that can generalize to unseen tasks using pre-collected data from related tasks. Recent approaches leverage the scalability of transformer architectures to model behavior sequences and support task adaptation using target task demonstrations. However, such data is often unavailable in real-world settings, where the task objective may be known but cannot be easily demonstrated. In contrast, humans routinely interpret and perform new tasks based solely on natural language instructions. In this work, we explore the potential of using natural language task descriptions to enable zero-shot task adaptation in offline meta-RL without requiring any data from the target task. We propose the Text-Guided Decision Transformer (TG-DT), a framework that enables zero-shot generalization by grounding policy learning in natural language. TG-DT learns a shared embedding space between task descriptions and behavioral trajectories via a dual contrastive and matching-based objective, ensuring robust alignment. A transformer-based policy is then conditioned on these aligned representations to generate task-appropriate actions. At test time, TG-DT synthesizes policies for unseen tasks using only their text descriptions and can optionally leverage a description-guided data sharing strategy to enhance adaptation. Experiments on standard offline meta-RL benchmarks, including MuJoCo and Meta-World, demonstrate that TG-DT achieves strong generalization to unseen tasks. 

   more » « less
2. In-Sample RL via Regularizing the Evaluation Gap

   Shen, H; Shen, W; Fox, R (July 2026, ICML)

   Distribution shift poses a fundamental challenge in offline reinforcement learning, often leading to value overestimation when querying out-ofdistribution actions. We introduce Regularized Evaluation Gap (REG) as a bridge between implicit methods like IQL and explicit conservative methods. We formulate policy evaluation as a robust optimization problem over an ambiguity set of critics and showthat IQL’s objective can be viewed as an approximate dual solution to this problem. To extract a policy from the learned value function, we propose a practical Orthogonal Policy Gradient (OPG) update. This method regularizes an aggressive, mode-seeking policy gradient by projecting it onto the subspace orthogonal to a stable, in-sample behavior cloning gradient. Extensive D4RL experiments demonstrate that REG matches state-of-the-art performance among both Gaussian methods and diffusion-based approaches without the computational burden of the latter.1 

   more » « less
3. Learning Off-policy for Online Planning

   Sikchi, Harshit; Zhou, Wenxuan; Held, David (January 2021, Conference on Robot Learning (CoRL))

   Reinforcement learning (RL) in low-data and risk-sensitive domains requires performant and flexible deployment policies that can readily incorporate constraints during deployment. One such class of policies are the semi-parametric H-step lookahead policies, which select actions using trajectory optimization over a dynamics model for a fixed horizon with a terminal value function. In this work, we investigate a novel instantiation of H-step lookahead with a learned model and a terminal value function learned by a model-free off-policy algorithm, named Learning Off-Policy with Online Planning (LOOP). We provide a theoretical analysis of this method, suggesting a tradeoff between model errors and value function errors and empirically demonstrate this tradeoff to be beneficial in deep reinforcement learning. Furthermore, we identify the "Actor Divergence" issue in this framework and propose Actor Regularized Control (ARC), a modified trajectory optimization procedure. We evaluate our method on a set of robotic tasks for Offline and Online RL and demonstrate improved performance. We also show the flexibility of LOOP to incorporate safety constraints during deployment with a set of navigation environments. We demonstrate that LOOP is a desirable framework for robotics applications based on its strong performance in various important RL settings. 

   more » « less
4. Offline Reinforcement Learning with Closed-Form Policy Improvement Operators

   Li, Jiachen and; Zhang, Edwin; Yin, Ming; Bai, Qinxun; Wang, Yu-Xiang; Wang, William Yang (July 2023, Proceedings of Machine Learning Research)

   Krause, Andreas and; Brunskill, Emma; Cho, Kyunghyun; Engelhardt, Barbara; Sabato, Sivan; Scarlett, Jonathan (Ed.)

   Behavior constrained policy optimization has been demonstrated to be a successful paradigm for tackling Offline Reinforcement Learning. By exploiting historical transitions, a policy is trained to maximize a learned value function while constrained by the behavior policy to avoid a significant distributional shift. In this paper, we propose our closed-form policy improvement operators. We make a novel observation that the behavior constraint naturally motivates the use of first-order Taylor approximation, leading to a linear approximation of the policy objective. Additionally, as practical datasets are usually collected by heterogeneous policies, we model the behavior policies as a Gaussian Mixture and overcome the induced optimization difficulties by leveraging the LogSumExp’s lower bound and Jensen’s Inequality, giving rise to a closed-form policy improvement operator. We instantiate both one-step and iterative offline RL algorithms with our novel policy improvement operators and empirically demonstrate their effectiveness over state-of-the-art algorithms on the standard D4RL benchmark. Our code is available at https://cfpi-icml23.github.io/. 

   more » « less
5. Offline Multi-task Transfer RL with Representational Penalization

   Bose, Avinandan; Du, Simon S; Fazel, Maryam (April 2025, Proceedings of Machine Learning Research)

   Li, Y; Mandt, S; Agrawal, S; Khan, E (Ed.)

   We study the problem of representational transfer in offline Reinforcement Learning (RL), where a learner has access to episodic data from a number of source tasks collected a priori, and aims to learn a shared representation to be used in finding a good policy for a target task. Unlike in online RL where the agent interacts with the environment while learning a policy, in the offline setting there cannot be such interactions in either the source tasks or the target task; thus multi-task offline RL can suffer from incomplete coverage. We propose an algorithm to compute pointwise uncertainty measures for the learnt representation in low-rank MDPs, and establish a data-dependent upper bound for the suboptimality of the learnt policy for the target task. Our algorithm leverages the collective exploration done by source tasks to mitigate poor coverage at some points by a few tasks, thus overcoming the limitation of needing uniformly good coverage for a meaningful transfer by existing offline algorithms. We complement our theoretical results with empirical evaluation on a rich-observation MDP which requires many samples for complete coverage. Our findings illustrate the benefits of penalizing and quantifying the uncertainty in the learnt representation. 

   more » « less