An official website of the United States government
Deep reinforcement learning (deep RL) has emerged as an effective tool for developing controllers for legged robots. However, vanilla deep RL often requires a tremendous amount of training samples and is not feasible for achieving robust behaviors. Instead, researchers have investigated a novel policy architecture by incorporating human experts' knowledge, such as Policies Modulating Trajectory Generators (PMTG). This architecture builds a recurrent control loop by combining a parametric trajectory generator (TG) and a feedback policy network to achieve more robust behaviors. In this work, we propose Policies Modulating Finite State Machine (PM-FSM) by replacing TGs with contact-aware finite state machines (FSM), which offers more flexible control of each leg. This invention offers an explicit notion of contact events to the policy to negotiate unexpected perturbations. We demonstrated that the proposed architecture could achieve more robust behaviors in various scenarios, such as challenging terrains or external perturbations, on both simulated and real robots.
more »
« less
This content will become publicly available on April 26, 2027
Neurosymbolic World Models for Sequential Decision Making
We present Structured World Modeling for Policy Optimization (SWMPO), a framework for unsupervised learning of neurosymbolic Finite State Machines (FSM) that capture environmental structure for policy optimization. Traditional unsupervised world modeling methods rely on unstructured representations, such as neural networks, that do not explicitly represent high-level patterns within the system (e.g., patterns in the dynamics of regions such as water and land). Instead, SWMPO models the environment as a finite state machine (FSM), where each state corresponds to a specific region with distinct dynamics. This structured representation can then be leveraged for tasks like policy optimization. Previous works that synthesize FSMs for this purpose have been limited to discrete spaces, not continuous spaces. Instead, our proposed FSM synthesis algorithm operates in an unsupervised manner, leveraging low-level features from unprocessed, non-visual data, making it adaptable across various domains. The synthesized FSM models are expressive enough to be used in a model-based Reinforcement Learning scheme that leverages offline data to efficiently synthesize environment-specific world models. We demonstrate the advantages of SWMPO by benchmarking its environment modeling capabilities in simulated environments.
more »
« less
- Award ID(s):
- 1918839
- PAR ID:
- 10679127
- Publisher / Repository:
- Proceedings of the 42nd International Conference on Machine Learning (ICML 2025)
- Date Published:
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Offline reinforcement learning (RL) has received increasing attention for learning policies from previously collected data without interaction with the real environment, which is particularly important in high-stakes applications. While a growing body of work has developed offline RL algorithms, these methods often rely on restrictive assumptions about data coverage and suffer from distribution shift. In this paper, we propose a residuals-based offline RL framework for general state and action spaces. Specifically, we define a residuals-based Bellman optimality operator that explicitly incorporates estimation error in learning transition dynamics into policy optimization by leveraging empirical residuals. We show that this Bellman operator is a contraction mapping and identify conditions under which its fixed point is asymptotically optimal and possesses finite-sample guarantees. We further develop a residuals-based offline deep Q-learning (DQN) algorithm. Using a stochastic CartPole environment, we demonstrate the effectiveness of our residuals-based offline DQN algorithm.more » « less
-
Verification of FPGA-based designs and comprehension of legacy designs can be aided by the process of reverse engineering the flattened Look-up Table (LUT) level netlists to high-level RTL representations. We propose a tool flow to extract Finite State Controllers by identifying control registers and progressively improving the accuracy of register classification. A control unit consists of one or more Finite State Machines (FSMs) which manage the execution of datapath units. The proposed tool flow has two phases. Phase 1 extracts the potential state/control registers. Phase 2 identifies the exact list of state/control registers and groups FSMs. The main goal of the proposed work is to improve the accuracy of control register identification. Three types of controllers used for experimental evaluation are standalone FSM designs with no datapath units, datapaths with a single FSM, and datapaths with multiple FSMs. Accuracy is observed to be 73% to 100% in controllers with multiple FSMs, 100% in controllers with a single FSM and standalone FSM controller designs. The average accuracy of control register detection over all the real-world designs considered is 98%.more » « less
-
Interpretable and Effective Reinforcement Learning for Attacking against Graph-based Rumor DetectionSocial networks are frequently polluted by rumors, which can be detected by advanced models such as graph neural networks. However, the models are vulnerable to attacks, and discovering and understanding the vulnerabilities is critical to robust rumor detection. To discover subtle vulnerabilities, we design a attacking algorithm based on reinforcement learning to camouflage rumors against black-box detectors. We address exponentially large state spaces, high-order graph dependencies, and ranking dependencies, which are unique to the problem setting but fundamentally challenging for the state-of-the-art end-to-end approaches. We design domain-specific features that have causal effect on the reward, so that even a linear policy can arrive at powerful attacks with additional interpretability. To speed up policy optimization, we devise: (i) a credit assignment method that proportionally decomposes delayed and aggregated rewards to atomic attacking actions for enhance feature-reward associations; (ii) a time-dependent control variate to reduce prediction variance due to large state-action spaces and long attack horizon, based on reward variance analysis and a Bayesian analysis of the prediction distribution. On two real world datasets of rumor detection tasks, we demonstrate: (i) the effectiveness of the learned attacking policy on a wide spectrum of target models compared to both rule-based and end-to-end attacking approaches; (ii) the usefulness of the proposed credit assignment strategy and variance reduction components; (iii) the interpretability of the attacking policy.more » « less
-
We formulate a unifying framework for *unsupervised continual learning (UCL)*, which disentangles learning objectives that are specific to the present and the past data, encompassing *stability*, *plasticity*, and *cross-task consolidation*. The framework reveals that many existing UCL approaches overlook cross-task consolidation and try to balance plasticity and stability in a shared embedding space. This results in worse performance due to a lack of within-task data diversity and reduced effectiveness in learning the current task. Our method, *Osiris*, which explicitly optimizes all three objectives on separate embedding spaces, achieves state-of-the-art performance on all benchmarks, including two novel ones proposed in this paper featuring semantically structured task sequences. Finally, we show some preliminary evidence that continual models can benefit from such more realistic learning scenarios.more » « less
