Handling Delay in Real-Time Reinforcement Learning

Real-time reinforcement learning (RL) introduces several challenges. First, policies are constrained to a fixed number of actions per second due to hardware limitations. Second, the environment may change while the network is still computing an action, leading to observational delay. The first issue can partly be addressed with pipelining, leading to higher throughput and potentially better policies. However, the second issue remains: if each neuron operates in parallel with an execution time of $\tau$, an $N$-layer feed-forward network experiences observation delay of $\tau N$. Reducing the number of layers can decrease this delay, but at the cost of the network's expressivity. In this work, we explore the trade-off between minimizing delay and network's expressivity. We present a theoretically motivated solution that leverages temporal skip connections combined with history-augmented observations. We evaluate several architectures and show that those incorporating temporal skip connections achieve strong performance across various neuron execution times, reinforcement learning algorithms, and environments, including four Mujoco tasks and all MinAtar games. Moreover, we demonstrate parallel neuron computation can accelerate inference by 6-350% on standard hardware. Our investigation into temporal skip connections and parallel computations paves the way for more efficient RL agents in real-time setting.

Behaviour Discovery and Attribution for Explainable Reinforcement Learning

Explaining the decisions made by reinforcement learning (RL) agents is critical for building trust and ensuring reliability in real-world applications. Traditional approaches to explainability often rely on saliency analysis, which can be limited in providing actionable insights. Recently, there has been growing interest in attributing RL decisions to specific trajectories within a dataset. However, these methods often generalize explanations to long trajectories, potentially involving multiple distinct behaviors. Often, providing multiple more fine grained explanations would improve clarity. In this work, we propose a framework for behavior discovery and action attribution to behaviors in offline RL trajectories. Our method identifies meaningful behavioral segments, enabling more precise and granular explanations associated with high level agent behaviors. This approach is adaptable across diverse environments with minimal modifications, offering a scalable and versatile solution for behavior discovery and attribution for explainable RL.

Comparative Analysis of Diffusion Generative Models in Computational Pathology

Diffusion Generative Models (DGM) have rapidly surfaced as emerging topics in the field of computer vision, garnering significant interest across a wide array of deep learning applications. Despite their high computational demand, these models are extensively utilized for their superior sample quality and robust mode coverage. While research in diffusion generative models is advancing, exploration within the domain of computational pathology and its large-scale datasets has been comparatively gradual. Bridging the gap between the high-quality generation capabilities of Diffusion Generative Models and the intricate nature of pathology data, this paper presents an in-depth comparative analysis of diffusion methods applied to a pathology dataset. Our analysis extends to datasets with varying Fields of View (FOV), revealing that DGMs are highly effective in producing high-quality synthetic data. An ablative study is also conducted, followed by a detailed discussion on the impact of various methods on the synthesized histopathology images. One striking observation from our experiments is how the adjustment of image size during data generation can simulate varying fields of view. These findings underscore the potential of DGMs to enhance the quality and diversity of synthetic pathology data, especially when used with real data, ultimately increasing accuracy of deep learning models in histopathology. Code is available from https://github.com/AtlasAnalyticsLab/Diffusion4Path

Adaptive Group Robust Ensemble Knowledge Distillation

Neural networks can learn spurious correlations in the data, often leading to performance disparity for underrepresented subgroups. Studies have demonstrated that the disparity is amplified when knowledge is distilled from a complex teacher model to a relatively "simple" student model. Prior work has shown that ensemble deep learning methods can improve the performance of the worst-case subgroups; however, it is unclear if this advantage carries over when distilling knowledge from an ensemble of teachers, especially when the teacher models are debiased. This study demonstrates that traditional ensemble knowledge distillation can significantly drop the performance of the worst-case subgroups in the distilled student model even when the teacher models are debiased. To overcome this, we propose Adaptive Group Robust Ensemble Knowledge Distillation (AGRE-KD), a simple ensembling strategy to ensure that the student model receives knowledge beneficial for unknown underrepresented subgroups. Leveraging an additional biased model, our method selectively chooses teachers whose knowledge would better improve the worst-performing subgroups by upweighting the teachers with gradient directions deviating from the biased model. Our experiments on several datasets demonstrate the superiority of the proposed ensemble distillation technique and show that it can even outperform classic model ensembles based on majority voting.

KD-LoRA: A Hybrid Approach to Efficient Fine-Tuning with LoRA and Knowledge Distillation

Large language models (LLMs) have demonstrated remarkable performance across various downstream tasks. However, the high computational and memory requirements of LLMs are a major bottleneck. To address this, parameter-efficient fine-tuning (PEFT) methods such as low-rank adaptation (LoRA) have been proposed to reduce computational costs while ensuring minimal loss in performance. Additionally, knowledge distillation (KD) has been a popular choice for obtaining compact student models from teacher models. In this work, we present KD-LoRA, a novel fine-tuning method that combines LoRA with KD. Our results demonstrate that KD-LoRA achieves performance comparable to full fine-tuning (FFT) and LoRA while significantly reducing resource requirements. Specifically, KD-LoRA retains 98% of LoRA's performance on the GLUE benchmark, while being 40% more compact. Additionally, KD-LoRA reduces GPU memory usage by 30% compared to LoRA, while decreasing inference time by 30% compared to both FFT and LoRA. We evaluate KD-LoRA across three encoder-only models: BERT, RoBERTa, and DeBERTaV3. Code is available at https://github.com/rambodazimi/KD-LoRA.

Prediction of Final Phosphorus Content of Steel in a Scrap-Based Electric Arc Furnace Using Artificial Neural Networks

The scrap-based electric arc furnace process is expected to capture a significant share of the steel market in the future due to its potential for reducing environmental impacts through steel recycling. However, managing impurities, particularly phosphorus, remains a challenge. This study aims to develop a machine learning model to estimate the steel phosphorus content at the end of the process based on input parameters. Data were collected over two years from a steel plant, focusing on the chemical composition and weight of the scrap, the volume of oxygen injected, and process duration. After preprocessing the data, several machine learning models were evaluated, with the artificial neural network (ANN) emerging as the most effective. The best ANN model included four hidden layers. The model was trained for 500 epochs with a batch size of 50. The best model achieves a mean square error (MSE) of 0.000016, a root-mean-square error (RMSE) of 0.0049998, a coefficient of determination (R2) of 99.96%, and a correlation coefficient (r) of 99.98%. Notably, the model achieved a 100% hit rate for predicting phosphorus content within +-0.001 wt% (+-10 ppm). These results demonstrate that the optimized ANN model offers accurate predictions for the steel final phosphorus content.

Learning Multi-agent Multi-machine Tending by Mobile Robots

Robotics can help address the growing worker shortage challenge of the manufacturing industry. As such, machine tending is a task collaborative robots can tackle that can also highly boost productivity. Nevertheless, existing robotics systems deployed in that sector rely on a fixed single-arm setup, whereas mobile robots can provide more flexibility and scalability. In this work, we introduce a multi-agent multi-machine tending learning framework by mobile robots based on Multi-agent Reinforcement Learning (MARL) techniques with the design of a suitable observation and reward. Moreover, an attention-based encoding mechanism is developed and integrated into Multi-agent Proximal Policy Optimization (MAPPO) algorithm to boost its performance for machine tending scenarios. Our model (AB-MAPPO) outperformed MAPPO in this new challenging scenario in terms of task success, safety, and resources utilization. Furthermore, we provided an extensive ablation study to support our various design decisions.

Empowering Clinicians with Medical Decision Transformers: A Framework for Sepsis Treatment

Offline reinforcement learning has shown promise for solving tasks in safety-critical settings, such as clinical decision support. Its application, however, has been limited by the lack of interpretability and interactivity for clinicians. To address these challenges, we propose the medical decision transformer (MeDT), a novel and versatile framework based on the goal-conditioned reinforcement learning paradigm for sepsis treatment recommendation. MeDT uses the decision transformer architecture to learn a policy for drug dosage recommendation. During offline training, MeDT utilizes collected treatment trajectories to predict administered treatments for each time step, incorporating known treatment outcomes, target acuity scores, past treatment decisions, and current and past medical states. This analysis enables MeDT to capture complex dependencies among a patient's medical history, treatment decisions, outcomes, and short-term effects on stability. Our proposed conditioning uses acuity scores to address sparse reward issues and to facilitate clinician-model interactions, enhancing decision-making. Following training, MeDT can generate tailored treatment recommendations by conditioning on the desired positive outcome (survival) and user-specified short-term stability improvements. We carry out rigorous experiments on data from the MIMIC-III dataset and use off-policy evaluation to demonstrate that MeDT recommends interventions that outperform or are competitive with existing offline reinforcement learning methods while enabling a more interpretable, personalized and clinician-directed approach.

Reinforcement Learning for Sequence Design Leveraging Protein Language Models

Protein sequence design, determined by amino acid sequences, are essential to protein engineering problems in drug discovery. Prior approaches have resorted to evolutionary strategies or Monte-Carlo methods for protein design, but often fail to exploit the structure of the combinatorial search space, to generalize to unseen sequences. In the context of discrete black box optimization over large search spaces, learning a mutation policy to generate novel sequences with reinforcement learning is appealing. Recent advances in protein language models (PLMs) trained on large corpora of protein sequences offer a potential solution to this problem by scoring proteins according to their biological plausibility (such as the TM-score). In this work, we propose to use PLMs as a reward function to generate new sequences. Yet the PLM can be computationally expensive to query due to its large size. To this end, we propose an alternative paradigm where optimization can be performed on scores from a smaller proxy model that is periodically finetuned, jointly while learning the mutation policy. We perform extensive experiments on various sequence lengths to benchmark RL-based approaches, and provide comprehensive evaluations along biological plausibility and diversity of the protein. Our experimental results include favorable evaluations of the proposed sequences, along with high diversity scores, demonstrating that RL is a strong candidate for biological sequence design. Finally, we provide a modular open source implementation can be easily integrated in most RL training loops, with support for replacing the reward model with other PLMs, to spur further research in this domain. The code for all experiments is provided in the supplementary material.

Learning to Play Atari in a World of Tokens

Model-based reinforcement learning agents utilizing transformers have shown improved sample efficiency due to their ability to model extended context, resulting in more accurate world models. However, for complex reasoning and planning tasks, these methods primarily rely on continuous representations. This complicates modeling of discrete properties of the real world such as disjoint object classes between which interpolation is not plausible. In this work, we introduce discrete abstract representations for transformer-based learning (DART), a sample-efficient method utilizing discrete representations for modeling both the world and learning behavior. We incorporate a transformer-decoder for auto-regressive world modeling and a transformer-encoder for learning behavior by attending to task-relevant cues in the discrete representation of the world model. For handling partial observability, we aggregate information from past time steps as memory tokens. DART outperforms previous state-of-the-art methods that do not use look-ahead search on the Atari 100k sample efficiency benchmark with a median human-normalized score of 0.790 and beats humans in 9 out of 26 games. We release our code at https://pranaval.github.io/DART/.