Search

In this paper, we present a nonlinear numerical investigation on the dynamical scalarization process of a Reissner-Nordstr\"om black hole, incorporating an axionic scalar potential within the framework of the Einstein-Maxwell-dilaton theory. By scrutinizing the evolution of the irreducible mass of the black hole and the value of scalar field on the apparent horizon across various parameters of the axionic potential, we elucidate the correlations between the final states of scalarized charged black hole and the axionic potential. We observe that the inclusion of the axionic potential can either decrease or increase the irreducible mass of the final scalarized black hole, depending on the strength of the coupling between the dilation and the electric invariant $F_{\mu\nu}F^{\mu\nu}$. Regarding the value of the scalar field on the apparent horizon, we find that it decreases with the inclusion of the axionic potential. Our results contribute to an important understanding of the dynamical scalarization of black holes and the potential configurations of scalar hair with various self-interactions., Comment: 8 pages, 5 figures

Exploring the universal structure of the gravitational path integral beyond semi-classical saddles and uncovering a compelling statistical interpretation of black hole thermodynamics have long been significant challenges. We investigate the statistical interpretation of the Kerr-AdS black hole thermodynamics through an ensemble-averaged theory. By extending the phase space to include all possible states with conical singularities in their Euclidean counterparts, we derive the probability distribution of different states inherited from the Euclidean gravitational path integral. Moreover, we can define a density matrix of all the states in the phase space. By ensemble-averaging over all states, we show that the black hole phase transition naturally arises in the semi-classical limit, just as in the Schwarzschild-AdS and Reissner-Nordstr\"om-AdS cases. Away from the semi-classical regime, the ensemble-averaged theory exhibits a notable deviation from the conventional phase transition. Expanding around the classical saddles yields the subleading-order correction to the Gibbs free energy, which is half of the Hawking temperature. We demonstrate that the half Hawking temperature correction is a universal feature inherent to black holes in asymptotically AdS spacetime. With the subleading-order correction to Gibbs free energy, we also suggest that the whole black hole thermodynamic should be corrected accordingly., Comment: 33 pages,9 figures, comments are welcome!

Recent research has showed that, by accounting for the nonlinear electrodynamic field effects on the motion of test charged particles, it is possible to destroy an extremal and near-extremal black hole [Phys.Rev.D 101 (2020) 12, 124067]. Inspired by this perspective, we explore the potential for the destruction of a nonsingular black hole within the framework of general relativity, where gravity couples with nonlinear electrodynamic field. By combining the theory of nonlinear electrodynamics in curved spacetime, we obtain the conserved charges for test charged particles, then investigate the possibility of destroying the event horizon of the Ay\'on--Beato Garc\'\i a (ABG) nonsingular black hole by test charged particle and complex scalar field. We obtain the intervals for the parameter of the particle and scalar field which allow us to destroy the event horizon of an extremal and near-extremal ABG black hole black hole. Due to the nonlinear electrodynamic field effects, both an extremal and near-extremal black hole can be destroyed. Interestingly, we find that the parameter intervals for the test charged particle and the test complex scalar field that can destroy the event horizon of an extremal black hole are identical. Importantly, as the ABG black hole is a nonsingular black hole, our findings remain consistent with the weak cosmic censorship conjecture and might provide a viable approach to observe the internal structure of a black hole., Comment: 21 pages

Motivated by the recent progress on the holographic dual of the extended thermodynamics for black holes in anti-de-Sitter (AdS) space, we investiggate the hologrphic thermodynamics for the five-dimensional neutral Gauss-Bonnet AdS black hole in the context of the anti-de Sitter/conformal field theory (AdS/CFT) correspondence. Through the extended bulk thermodynamics for the five-dimensional Gauss-Bonnet AdS black hole, we derive the first law of the CFT thermodynamics which is obtained by directly translating the arbitrary conformal factors in the dual CFT. In addition to the newly defined chemical potential $\mu$ conjugating to the central charge $C$, we obtain other pairs of thermodynamics for the CFT, such as the temperature $\tilde{T}$ and the entropy $S$, the Gauss-Bonnet coupling constant $\tilde{\alpha}$ and its conjugate variable $ \tilde{\mathcal{A}}$, the pressure $\mathcal{P}$ and its conjugate volume $\mathcal{V}$. In the fixed $C$, $\mathcal{V}$ and $\tilde{\alpha}$ canonical ensemble, we obtain the canonical description of the CFT thermodynamics and observe the standard swallowtail behavior in the Helmholtz free energy vs the temperature plot. The self-intersection point of the Helmholtz free energy indicates the phase transition between the high and low entropy states of the CFT. By using Maxwell's equal area law, we get the critical point and coexistence curve for the high and low entropy phases of the CFT. Besides, we get the critical exponents for the CFT, and find that the critical point and critical exponents associated with the $\tilde{T}-S$ criticality of the CFT are the same as those of the five-dimensional Gauss-Bonnet AdS black hole., Comment: 22 pages,5 figures

Reinforcement learning (RL) trains agents to accomplish complex tasks through environmental interaction data, but its capacity is also limited by the scope of the available data. To obtain a knowledgeable agent, a promising approach is to leverage the knowledge from large language models (LLMs). Despite previous studies combining LLMs with RL, seamless integration of the two components remains challenging due to their semantic gap. This paper introduces a novel method, Knowledgeable Agents from Language Model Rollouts (KALM), which extracts knowledge from LLMs in the form of imaginary rollouts that can be easily learned by the agent through offline reinforcement learning methods. The primary challenge of KALM lies in LLM grounding, as LLMs are inherently limited to textual data, whereas environmental data often comprise numerical vectors unseen to LLMs. To address this, KALM fine-tunes the LLM to perform various tasks based on environmental data, including bidirectional translation between natural language descriptions of skills and their corresponding rollout data. This grounding process enhances the LLM's comprehension of environmental dynamics, enabling it to generate diverse and meaningful imaginary rollouts that reflect novel skills. Initial empirical evaluations on the CLEVR-Robot environment demonstrate that KALM enables agents to complete complex rephrasings of task goals and extend their capabilities to novel tasks requiring unprecedented optimal behaviors. KALM achieves a success rate of 46% in executing tasks with unseen goals, substantially surpassing the 26% success rate achieved by baseline methods. Furthermore, KALM effectively enables the LLM to comprehend environmental dynamics, resulting in the generation of meaningful imaginary rollouts that reflect novel skills and demonstrate the seamless integration of large language models and reinforcement learning.

The rise of large language models (LLMs) has revolutionized the way that we interact with artificial intelligence systems through natural language. However, LLMs often misinterpret user queries because of their uncertain intention, leading to less helpful responses. In natural human interactions, clarification is sought through targeted questioning to uncover obscure information. Thus, in this paper, we introduce LaMAI (Language Model with Active Inquiry), designed to endow LLMs with this same level of interactive engagement. LaMAI leverages active learning techniques to raise the most informative questions, fostering a dynamic bidirectional dialogue. This approach not only narrows the contextual gap but also refines the output of the LLMs, aligning it more closely with user expectations. Our empirical studies, across a variety of complex datasets where LLMs have limited conversational context, demonstrate the effectiveness of LaMAI. The method improves answer accuracy from 31.9% to 50.9%, outperforming other leading question-answering frameworks. Moreover, in scenarios involving human participants, LaMAI consistently generates responses that are superior or comparable to baseline methods in more than 82% of the cases. The applicability of LaMAI is further evidenced by its successful integration with various LLMs, highlighting its potential for the future of interactive language models.

Imitation learning (IL) enables agents to mimic expert behaviors. Most previous IL techniques focus on precisely imitating one policy through mass demonstrations. However, in many applications, what humans require is the ability to perform various tasks directly through a few demonstrations of corresponding tasks, where the agent would meet many unexpected changes when deployed. In this scenario, the agent is expected to not only imitate the demonstration but also adapt to unforeseen environmental changes. This motivates us to propose a new topic called imitator learning (ItorL), which aims to derive an imitator module that can on-the-fly reconstruct the imitation policies based on very limited expert demonstrations for different unseen tasks, without any extra adjustment. In this work, we focus on imitator learning based on only one expert demonstration. To solve ItorL, we propose Demo-Attention Actor-Critic (DAAC), which integrates IL into a reinforcement-learning paradigm that can regularize policies' behaviors in unexpected situations. Besides, for autonomous imitation policy building, we design a demonstration-based attention architecture for imitator policy that can effectively output imitated actions by adaptively tracing the suitable states in demonstrations. We develop a new navigation benchmark and a robot environment for \topic~and show that DAAC~outperforms previous imitation methods \textit{with large margins} both on seen and unseen tasks.

Stimulated by the recent researches of black hole thermodynamics for black hole with Newman-Unti-Tamburino (NUT) parameter, we investigate the thermodynamics and weak cosmic censorship conjecture for a Kerr-Newman Taub-NUT black hole. By defining the electric charge as a Komar integral over the event horizon, we construct a consistent first law of black hole thermodynamics for a Kerr-Newman Taub-NUT black hole through Euclidean action. Having the first law of black hole thermodynamics, we investigate the weak cosmic censorship conjecture for the black hole with a charged test particle and a complex scalar field. We find that an extremal black hole cannot be destroyed by a charged test particle and a complex scalar field. For a near-extremal black hole with small NUT parameter, it can be destroyed by a charged test particle but cannot be destroyed by a complex scalar field., Comment: 12 pages,3 figures,published version

Natural Language-conditioned reinforcement learning (RL) enables the agents to follow human instructions. Previous approaches generally implemented language-conditioned RL by providing human instructions in natural language (NL) and training a following policy. In this outside-in approach, the policy needs to comprehend the NL and manage the task simultaneously. However, the unbounded NL examples often bring much extra complexity for solving concrete RL tasks, which can distract policy learning from completing the task. To ease the learning burden of the policy, we investigate an inside-out scheme for natural language-conditioned RL by developing a task language (TL) that is task-related and unique. The TL is used in RL to achieve highly efficient and effective policy training. Besides, a translator is trained to translate NL into TL. We implement this scheme as TALAR (TAsk Language with predicAte Representation) that learns multiple predicates to model object relationships as the TL. Experiments indicate that TALAR not only better comprehends NL instructions but also leads to a better instruction-following policy that improves 13.4% success rate and adapts to unseen expressions of NL instruction. The TL can also be an effective task abstraction, naturally compatible with hierarchical RL.

The mature soybean plants are of complex architecture with pods frequently touching each other, posing a challenge for in-situ segmentation of on-branch soybean pods. Deep learning-based methods can achieve accurate training and strong generalization capabilities, but it demands massive labeled data, which is often a limitation, especially for agricultural applications. As lacking the labeled data to train an in-situ segmentation model for on-branch soybean pods, we propose a transfer learning from synthetic in-vitro soybean pods. First, we present a novel automated image generation method to rapidly generate a synthetic in-vitro soybean pods dataset with plenty of annotated samples. The in-vitro soybean pods samples are overlapped to simulate the frequently physically touching of on-branch soybean pods. Then, we design a two-step transfer learning. In the first step, we finetune an instance segmentation network pretrained by a source domain (MS COCO dataset) with a synthetic target domain (in-vitro soybean pods dataset). In the second step, transferring from simulation to reality is performed by finetuning on a few real-world mature soybean plant samples. The experimental results show the effectiveness of the proposed two-step transfer learning method, such that AP$_{50}$ was 0.80 for the real-world mature soybean plant test dataset, which is higher than that of direct adaptation and its AP$_{50}$ was 0.77. Furthermore, the visualizations of in-situ segmentation results of on-branch soybean pods show that our method performs better than other methods, especially when soybean pods overlap densely., Comment: Accepted by CVPR 2022 Vision for Agriculture Workshop

The destruction of the event horizon of a nonsingular black hole, which is not prevented by the weak cosmic censorship conjecture, might provide us the possibility to access quantum regime of gravity inside black hole. We investigate the possibility of overspinning a nonsingular rotating quantum-corrected black hole by a test particle and a scalar field in this paper, and analyse the effect of the quantum parameter on the destruction of the event horizon. For the test particle injection, both extremal and near-extremal black holes cannot be overspun due to the existence of the quantum parameter. And the larger the quantum parameter the harder the black hole to be overspun. It seems that the quantum parameter acts as a protector to prevent the black hole to be destroyed. However, for the test scalar field scattering, both extremal and near-extremal black holes can be destroyed. Due to the loop quantum gravity correction, the angular velocity of the extremal black hole shifts from that of the extremal Kerr black hole. This provides a small range of wave modes to destroy the event horizon of the quantum-corrected black hole., Comment: 19 pages, 1 figure, published version