Safe reinforcement learning tasks with multiple constraints are a challenging domain despite being very common in the real world. In safety-critical domains, properly handling the constraints becomes even more important. To address this challenge, we first describe the multi-constraint problem with a stronger Uniformly Constrained MDP (UCMDP) model; we then propose Objective Suppression, a novel method that adaptively suppresses the task reward maximizing objectives according to a safety critic, as a solution to the Lagrangian dual of a UCMDP. We benchmark Objective Suppression in two multi-constraint safety domains, including an autonomous driving domain where any incorrect behavior can lead to disastrous consequences. Empirically, we demonstrate that our proposed method, when combined with existing safe RL algorithms, can match the task reward achieved by our baselines with significantly fewer constraint violations.

Text-based reinforcement learning involves an agent interacting with a fictional environment using observed text and admissible actions in natural language to complete a task. Previous works have shown that agents can succeed in text-based interactive environments even in the complete absence of semantic understanding or other linguistic capabilities. The success of these agents in playing such games suggests that semantic understanding may not be important for the task. This raises an important question about the benefits of LMs in guiding the agents through the game states. In this work, we show that rich semantic understanding leads to efficient training of text-based RL agents. Moreover, we describe the occurrence of semantic degeneration as a consequence of inappropriate fine-tuning of language models in text-based reinforcement learning (TBRL). Specifically, we describe the shift in the semantic representation of words in the LM, as well as how it affects the performance of the agent in tasks that are semantically similar to the training games. We believe these results may help develop better strategies to fine-tune agents in text-based RL scenarios.

In this work, we address the challenge of zero-shot generalization (ZSG) in Reinforcement Learning (RL), where agents must adapt to entirely novel environments without additional training. We argue that understanding and utilizing contextual cues, such as the gravity level of the environment, is critical for robust generalization, and we propose to integrate the learning of context representations directly with policy learning. Our algorithm demonstrates improved generalization on various simulated domains, outperforming prior context-learning techniques in zero-shot settings. By jointly learning policy and context, our method acquires behavior-specific context representations, enabling adaptation to unseen environments and marks progress towards reinforcement learning systems that generalize across diverse real-world tasks.

Embodied visual tracking is to follow a target object in dynamic 3D environments using an agent's egocentric vision. This is a vital and challenging skill for embodied agents. However, existing methods suffer from inefficient training and poor generalization. In this paper, we propose a novel framework that combines visual foundation models (VFM) and offline reinforcement learning (offline RL) to empower embodied visual tracking. We use a pre-trained VFM, such as ``Tracking Anything", to extract semantic segmentation masks with text prompts. We then train a recurrent policy network with offline RL, e.g., Conservative Q-Learning, to learn from the collected demonstrations without online agent-environment interactions. To further improve the robustness and generalization of the policy network, we also introduce a mask re-targeting mechanism and a multi-level data collection strategy. In this way, we can train a robust tracker within an hour on a consumer-level GPU, e.g., Nvidia RTX 3090. Such efficiency is unprecedented for RL-based visual tracking methods. We evaluate our tracker on several high-fidelity environments with challenging situations, such as distraction and occlusion. The results show that our agent outperforms state-of-the-art methods in terms of sample efficiency, robustness to distractors, and generalization to unseen scenarios and targets. We also demonstrate the transferability of the learned tracker from the virtual world to real-world scenarios.

Transit agencies world-wide face tightening budgets. To maintain quality of service while cutting costs, efficient transit network design is essential. But planning a network of public transit routes is a challenging optimization problem. The most successful approaches to date use metaheuristic algorithms to search through the space of possible transit networks by applying low-level heuristics that randomly alter routes in a network. The design of these low-level heuristics has a major impact on the quality of the result. In this paper we use deep reinforcement learning with graph neural nets to learn low-level heuristics for an evolutionary algorithm, instead of designing them manually. These learned heuristics improve the algorithm's results on benchmark synthetic cities with 70 nodes or more, and obtain state-of-the-art results when optimizing operating costs. They also improve upon a simulation of the real transit network in the city of Laval, Canada, by as much as 54% and 18% on two key metrics, and offer cost savings of up to 12% over the city's existing transit network.

Although Reinforcement Learning (RL) algorithms acquire sequential behavioral patterns through interactions with the environment, their effectiveness in noisy and high-dimensional scenarios typically relies on specific structural priors. In this paper, we propose a novel and general Structural Information principles-based framework for effective Decision-Making, namely SIDM, approached from an information-theoretic perspective. This paper presents a specific unsupervised partitioning method that forms vertex communities in the state and action spaces based on their feature similarities. An aggregation function, which utilizes structural entropy as the vertex weight, is devised within each community to obtain its embedding, thereby facilitating hierarchical state and action abstractions. By extracting abstract elements from historical trajectories, a directed, weighted, homogeneous transition graph is constructed. The minimization of this graph's high-dimensional entropy leads to the generation of an optimal encoding tree. An innovative two-layer skill-based learning mechanism is introduced to compute the common path entropy of each state transition as its identified probability, thereby obviating the requirement for expert knowledge. Moreover, SIDM can be flexibly incorporated into various single-agent and multi-agent RL algorithms, enhancing their performance. Finally, extensive evaluations on challenging benchmarks demonstrate that, compared with SOTA baselines, our framework significantly and consistently improves the policy's quality, stability, and efficiency up to 32.70%, 88.26%, and 64.86%, respectively.

Ultrasound (US) has been widely used in daily clinical practice for screening internal organs and guiding interventions. However, due to the acoustic shadow cast by the subcutaneous rib cage, the US examination for thoracic application is still challenging. To fully cover and reconstruct the region of interest in US for diagnosis, an intercostal scanning path is necessary. To tackle this challenge, we present a reinforcement learning (RL) approach for planning scanning paths between ribs to monitor changes in lesions on internal organs, such as the liver and heart, which are covered by rib cages. Structured anatomical information of the human skeleton is crucial for planning these intercostal paths. To obtain such anatomical insight, an RL agent is trained in a virtual environment constructed using computational tomography (CT) templates with randomly initialized tumors of various shapes and locations. In addition, task-specific state representation and reward functions are introduced to ensure the convergence of the training process while minimizing the effects of acoustic attenuation and shadows during scanning. To validate the effectiveness of the proposed approach, experiments have been carried out on unseen CTs with randomly defined single or multiple scanning targets. The results demonstrate the efficiency of the proposed RL framework in planning non-shadowed US scanning trajectories in areas with limited acoustic access.

One of the notorious issues for Reinforcement Learning (RL) is poor sample efficiency. Compared to single agent RL, the sample efficiency for Multi-Agent Reinforcement Learning (MARL) is more challenging because of its inherent partial observability, non-stationary training, and enormous strategy space. Although much effort has been devoted to developing new methods and enhancing sample efficiency, we look at the widely used episodic training mechanism. In each training step, tens of frames are collected, but only one gradient step is made. We argue that this episodic training could be a source of poor sample efficiency. To better exploit the data already collected, we propose to increase the frequency of the gradient updates per environment interaction (a.k.a. Replay Ratio or Update-To-Data ratio). To show its generality, we evaluate $3$ MARL methods on $6$ SMAC tasks. The empirical results validate that a higher replay ratio significantly improves the sample efficiency for MARL algorithms. The codes to reimplement the results presented in this paper are open-sourced at https://anonymous.4open.science/r/rr_for_MARL-0D83/.

This note clarifies some confusions (and perhaps throws out more) around model-based reinforcement learning and their theoretical understanding in the context of deep RL. Main topics of discussion are (1) how to reconcile model-based RL's bad empirical reputation on error compounding with its superior theoretical properties, and (2) the limitations of empirically popular losses. For the latter, concrete counterexamples for the "MuZero loss" are constructed to show that it not only fails in stochastic environments, but also suffers exponential sample complexity in deterministic environments when data provides sufficient coverage.

This paper presents the first algorithm for model-based offline quantum reinforcement learning and demonstrates its functionality on the cart-pole benchmark. The model and the policy to be optimized are each implemented as variational quantum circuits. The model is trained by gradient descent to fit a pre-recorded data set. The policy is optimized with a gradient-free optimization scheme using the return estimate given by the model as the fitness function. This model-based approach allows, in principle, full realization on a quantum computer during the optimization phase and gives hope that a quantum advantage can be achieved as soon as sufficiently powerful quantum computers are available.