In the astronomical observation field, determining the allocation of observation resources of the telescope array and planning follow-up observations for targets of opportunity (ToOs) are indispensable components of astronomical scientific discovery. This problem is computationally challenging, given the online observation setting and the abundance of time-varying factors that can affect whether an observation can be conducted. This paper presents ROARS, a reinforcement learning approach for online astronomical resource-constrained scheduling. To capture the structure of the astronomical observation scheduling, we depict every schedule using a directed acyclic graph (DAG), illustrating the dependency of timing between different observation tasks within the schedule. Deep reinforcement learning is used to learn a policy that can improve the feasible solution by iteratively local rewriting until convergence. It can solve the challenge of obtaining a complete solution directly from scratch in astronomical observation scenarios, due to the high computational complexity resulting from numerous spatial and temporal constraints. A simulation environment is developed based on real-world scenarios for experiments, to evaluate the effectiveness of our proposed scheduling approach. The experimental results show that ROARS surpasses 5 popular heuristics, adapts to various observation scenarios and learns effective strategies with hindsight.

Efficient Service Function Chain (SFC) provisioning and Virtual Network Function (VNF) placement are critical for enhancing network performance in modern architectures such as Software-Defined Networking (SDN) and Network Function Virtualization (NFV). While Deep Reinforcement Learning (DRL) aids decision-making in dynamic network environments, its reliance on structured inputs and predefined rules limits adaptability in unforeseen scenarios. Additionally, incorrect actions by a DRL agent may require numerous training iterations to correct, potentially reinforcing suboptimal policies and degrading performance. This paper integrates DRL with Language Models (LMs), specifically Bidirectional Encoder Representations from Transformers (BERT) and DistilBERT, to enhance network management. By feeding final VNF allocations from DRL into the LM, the system can process and respond to queries related to SFCs, DCs, and VNFs, enabling real-time insights into resource utilization, bottleneck detection, and future demand planning. The LMs are fine-tuned to our domain-specific dataset using Low-Rank Adaptation (LoRA). Results show that BERT outperforms DistilBERT with a lower test loss (0.28 compared to 0.36) and higher confidence (0.83 compared to 0.74), though BERT requires approximately 46% more processing time.

In this work, we conducted research on deformable object manipulation by robots based on demonstration-enhanced reinforcement learning (RL). To improve the learning efficiency of RL, we enhanced the utilization of demonstration data from multiple aspects and proposed the HGCR-DDPG algorithm. It uses a novel high-dimensional fuzzy approach for grasping-point selection, a refined behavior-cloning method to enhance data-driven learning in Rainbow-DDPG, and a sequential policy-learning strategy. Compared to the baseline algorithm (Rainbow-DDPG), our proposed HGCR-DDPG achieved 2.01 times the global average reward and reduced the global average standard deviation to 45% of that of the baseline algorithm. To reduce the human labor cost of demonstration collection, we proposed a low-cost demonstration collection method based on Nonlinear Model Predictive Control (NMPC). Simulation experiment results show that demonstrations collected through NMPC can be used to train HGCR-DDPG, achieving comparable results to those obtained with human demonstrations. To validate the feasibility of our proposed methods in real-world environments, we conducted physical experiments involving deformable object manipulation. We manipulated fabric to perform three tasks: diagonal folding, central axis folding, and flattening. The experimental results demonstrate that our proposed method achieved success rates of 83.3%, 80%, and 100% for these three tasks, respectively, validating the effectiveness of our approach. Compared to current large-model approaches for robot manipulation, the proposed algorithm is lightweight, requires fewer computational resources, and offers task-specific customization and efficient adaptability for specific tasks.

Numerous real-world control problems involve dynamics and objectives affected by unobservable hidden parameters, ranging from autonomous driving to robotic manipulation, which cause performance degradation during sim-to-real transfer. To represent these kinds of domains, we adopt hidden-parameter Markov decision processes (HIP-MDPs), which model sequential decision problems where hidden variables parameterize transition and reward functions. Existing approaches, such as domain randomization, domain adaptation, and meta-learning, simply treat the effect of hidden parameters as additional variance and often struggle to effectively handle HIP-MDP problems, especially when the rewards are parameterized by hidden variables. We introduce Privileged-Dreamer, a model-based reinforcement learning framework that extends the existing model-based approach by incorporating an explicit parameter estimation module. PrivilegedDreamer features its novel dual recurrent architecture that explicitly estimates hidden parameters from limited historical data and enables us to condition the model, actor, and critic networks on these estimated parameters. Our empirical analysis on five diverse HIP-MDP tasks demonstrates that PrivilegedDreamer outperforms state-of-the-art model-based, model-free, and domain adaptation learning algorithms. Additionally, we conduct ablation studies to justify the inclusion of each component in the proposed architecture.

Group-agent reinforcement learning (GARL) is a newly arising learning scenario, where multiple reinforcement learning agents study together in a group, sharing knowledge in an asynchronous fashion. The goal is to improve the learning performance of each individual agent. Under a more general heterogeneous setting where different agents learn using different algorithms, we advance GARL by designing novel and effective group-learning mechanisms. They guide the agents on whether and how to learn from action choices from the others, and allow the agents to adopt available policy and value function models sent by another agent if they perform better. We have conducted extensive experiments on a total of 43 different Atari 2600 games to demonstrate the superior performance of the proposed method. After the group learning, among the 129 agents examined, 96% are able to achieve a learning speed-up, and 72% are able to learn over 100 times faster. Also, around 41% of those agents have achieved a higher accumulated reward score by learning in less than 5% of the time steps required by a single agent when learning on its own.

Policy Space Response Oracles (PSRO) interleaves empirical game-theoretic analysis with deep reinforcement learning (DRL) to solve games too complex for traditional analytic methods. Tree-exploiting PSRO (TE-PSRO) is a variant of this approach that iteratively builds a coarsened empirical game model in extensive form using data obtained from querying a simulator that represents a detailed description of the game. We make two main methodological advances to TE-PSRO that enhance its applicability to complex games of imperfect information. First, we introduce a scalable representation for the empirical game tree where edges correspond to implicit policies learned through DRL. These policies cover conditions in the underlying game abstracted in the game model, supporting sustainable growth of the tree over epochs. Second, we leverage extensive form in the empirical model by employing refined Nash equilibria to direct strategy exploration. To enable this, we give a modular and scalable algorithm based on generalized backward induction for computing a subgame perfect equilibrium (SPE) in an imperfect-information game. We experimentally evaluate our approach on a suite of games including an alternating-offer bargaining game with outside offers; our results demonstrate that TE-PSRO converges toward equilibrium faster when new strategies are generated based on SPE rather than Nash equilibrium, and with reasonable time/memory requirements for the growing empirical model.

Deep Reinforcement Learning (RL) is remarkably effective in addressing sequential resource allocation problems in domains such as healthcare, public policy, and resource management. However, deep RL policies often lack transparency and adaptability, challenging their deployment alongside human decision-makers. In contrast, Language Agents, powered by large language models (LLMs), provide human-understandable reasoning but may struggle with effective decision making. To bridge this gap, we propose Rule-Bottleneck Reinforcement Learning (RBRL), a novel framework that jointly optimizes decision and explanations. At each step, RBRL generates candidate rules with an LLM, selects among them using an attention-based RL policy, and determines the environment action with an explanation via chain-of-thought reasoning. The RL rule selection is optimized using the environment rewards and an explainability metric judged by the LLM. Evaluations in real-world scenarios highlight RBRL's competitive performance with deep RL and efficiency gains over LLM fine-tuning. A survey further confirms the enhanced quality of its explanations.

Zero-shot reinforcement learning (RL) methods aim at instantly producing a behavior for an RL task in a given environment, from a description of the reward function. These methods are usually tested by evaluating their average performance on a series of downstream tasks. Yet they cannot be trained directly for that objective, unless the distribution of downstream tasks is known. Existing approaches either use other learning criteria [BBQ+ 18, TRO23, TO21, HDB+ 19], or explicitly set a prior on downstream tasks, such as reward functions given by a random neural network [FPAL24]. Here we prove that the zero-shot RL loss can be optimized directly, for a range of non-informative priors such as white noise rewards, temporally smooth rewards, ``scattered'' sparse rewards, or a combination of those. Thus, it is possible to learn the optimal zero-shot features algorithmically, for a wide mixture of priors. Surprisingly, the white noise prior leads to an objective almost identical to the one in VISR [HDB+19], via a different approach. This shows that some seemingly arbitrary choices in VISR, such as Von Mises--Fisher distributions, do maximize downstream performance. This also suggests more efficient ways to tackle the VISR objective. Finally, we discuss some consequences and limitations of the zero-shot RL objective, such as its tendency to produce narrow optimal features if only using Gaussian dense reward priors.

OpenAI o1 has shown that applying reinforcement learning to integrate reasoning steps directly during inference can significantly improve a model's reasoning capabilities. This result is exciting as the field transitions from the conventional autoregressive method of generating answers to a more deliberate approach that models the slow-thinking process through step-by-step reasoning training. Reinforcement learning plays a key role in both the model's training and decoding processes. In this article, we present a comprehensive formulation of reasoning problems and investigate the use of both model-based and model-free approaches to better support this slow-thinking framework.

Attention is fundamental to both biological and artificial intelligence, yet research on animal attention and AI self attention remains largely disconnected. We propose a Recurrent Vision Transformer (Recurrent ViT) that integrates self-attention with recurrent memory, allowing both current inputs and stored information to guide attention allocation. Trained solely via sparse reward feedback on a spatially cued orientation change detection task, a paradigm used in primate studies, our model exhibits primate like signatures of attention, including improved accuracy and faster responses for cued stimuli that scale with cue validity. Analysis of self-attention maps reveals dynamic spatial prioritization with reactivation prior to expected changes, and targeted perturbations produce performance shifts similar to those observed in primate frontal eye fields and superior colliculus. These findings demonstrate that incorporating recurrent feedback into self attention can capture key aspects of primate visual attention.