More Like this

1. Instructing Goal-Conditioned Reinforcement Learning Agents with Temporal Logic Objectives

   Qiu, Wenjie; Mao, Wensen; Zhu, He (December 2023, Advances in Neural Information Processing Systems (NeurIPS))

   Goal-conditioned reinforcement learning (RL) is a powerful approach for learning general-purpose skills by reaching diverse goals. However, it has limitations when it comes to task-conditioned policies, where goals are specified by temporally extended instructions written in the Linear Temporal Logic (LTL) formal language. Existing approaches for finding LTL-satisfying policies rely on sampling a large set of LTL instructions during training to adapt to unseen tasks at inference time. However, these approaches do not guarantee generalization to out-of-distribution LTL objectives, which may have increased complexity. In this paper, we propose a novel approach to address this challenge. We show that simple goal-conditioned RL agents can be instructed to follow arbitrary LTL specifications without additional training over the LTL task space. Unlike existing approaches that focus on LTL specifications expressible as regular expressions, our technique is unrestricted and generalizes to ω-regular expressions. Experiment results demonstrate the effectiveness of our approach in adapting goal-conditioned RL agents to satisfy complex temporal logic task specifications zero-shot. 

   more » « less
2. Combining Neural Networks and Tree Search for Task and Motion Planning in Challenging Environments

   Chris Paxton, Vasumathi Raman (January 2017, IROS 17/RLDM 17:)

   Task and motion planning subject to linear temporal logic (LTL) specifications in complex, dynamic environments requires efficient exploration of many possible future worlds. model‐free reinforcement learning has proven successful in a number of challenging tasks, but shows poor performance on tasks that require long‐term planning. in this work, we integrate Monte Carlo tree search with hierarchical neural net policies trained on expressive LTL specifications. we use reinforcement learning to find deep neural networks representing both low‐level control policies and task‐level ``option policies'' that achieve high‐level goals. our combined architecture generates safe and responsive motion plans that respect theLTL constraints. we demonstrate our approach in a simulated autonomous driving setting, where a vehicle must drive down a road in traffic, avoid collisions, and navigate an intersection, all while obeying rules of the road. 

   more » « less
3. Environment-Independent Task Specifications via GLTL

   Littman, Michael L.; Topcu, Ufuk; Fu, Jie; Isbell, Charles; Wen, Min; MacGlashan, James (April 2017, arXiv.org)

   We propose a new task-specification language for Markov decision processes that is designed to be an improvement over reward functions by being environment independent. The language is a variant of Linear Temporal Logic (LTL) that is extended to probabilistic specifications in a way that permits approximations to be learned in finite time. We provide several small environments that demonstrate the advantages of our geometric LTL (GLTL) language and illustrate how it can be used to specify standard reinforcement-learning tasks straightforwardly. 

   more » « less
4. Efficient Exploration and Discriminative World Model Learning with an Object-Centric Abstraction

   GX-Chen, Anthony; Marino, Kenneth; Fergus, Rob (April 2025, 2025 International Conference on Learning Representations (ICLR 2025))

   In the face of difficult exploration problems in reinforcement learning, we study whether giving an agent an object-centric mapping (describing a set of items and their attributes) allow for more efficient learning. We found this problem is best solved hierarchically by modelling items at a higher level of state abstraction to pixels, and attribute change at a higher level of temporal abstraction to primitive actions. This abstraction simplifies the transition dynamic by making specific future states easier to predict. We make use of this to propose a fully model-based algorithm that learns a discriminative world model, plans to explore efficiently with only a count-based intrinsic reward, and can subsequently plan to reach any discovered (abstract) states. We demonstrate the model's ability to (i) efficiently solve single tasks, (ii) transfer zero-shot and few-shot across item types and environments, and (iii) plan across long horizons. Across a suite of 2D crafting and MiniHack environments, we empirically show our model significantly out-performs state-of-the-art low-level methods (without abstraction), as well as performant model-free and model-based methods using the same abstraction. Finally, we show how to learn low level object-perturbing policies via reinforcement learning, and the object mapping itself by supervised learning. 

   more » « less
5. Policy Optimization with Linear Temporal Logic Constraints

   Cameron Voloshin; Hoang M. Le; Swarat Chaudhuri; Yisong Yue (January 2023, 36th Conference on Neural Information Processing Systems (NeurIPS 2022))

   We study the problem of policy optimization (PO) with linear temporal logic (LTL) constraints. The language of LTL allows flexible description of tasks that may be unnatural to encode as a scalar cost function. We consider LTL-constrained PO as a systematic framework, decoupling task specification from policy selection, and as an alternative to the standard of cost shaping. With access to a generative model, we develop a model-based approach that enjoys a sample complexity analysis for guaranteeing both task satisfaction and cost optimality (through a reduction to a reachability problem). Empirically, our algorithm can achieve strong performance even in low-sample regimes. 

   more » « less