-
Obey, Diverge, Collapse: Blind Obedience to Incorrect Instructions Drives Code LLMs to Irrecoverable Code Semantic Collapse
Authors:
Raj Jaiswal,
Anany Singh Divy,
Savar Bhasin,
Adi Bajpai,
Tanuja Ganu,
Rajiv Ratn Shah
Abstract:
Code language models are now trusted collaborators in production workflows for debugging, refactoring, and iterative repair, and every benchmark that evaluates them assumes the instructions they act on are correct. We study what happens when that assumption breaks. We evaluate code language models across four experiments designed to assess whether models resist or obey incorrect instructions in si…
▽ More
Code language models are now trusted collaborators in production workflows for debugging, refactoring, and iterative repair, and every benchmark that evaluates them assumes the instructions they act on are correct. We study what happens when that assumption breaks. We evaluate code language models across four experiments designed to assess whether models resist or obey incorrect instructions in single-pass and iterative repair settings, using the RunBugRun dataset of algorithmic Python problems with deterministic test cases. Our findings reveal a striking behavioral pattern: models correctly identify an incorrect instruction as wrong, then follow it anyway. This compliance unknowingly introduces errors beyond the original bug, and the corrupted code state cannot be recovered through subsequent self-guided iterative repair, which fails to converge across passes. We term this Blind Obedience, characterize the Ghost (Unknown) Errors it introduces, quantify the proportion of cases where semantic corruption proves irrecoverable, and show that extended reasoning cannot reverse it. These findings surface behavioral properties invisible to pass-rate evaluation, with direct consequences for code language models deployed in production settings.
△ Less
Submitted 5 July, 2026;
originally announced July 2026.
-
Waking Up Blind: Cold-Start Optimization of Supervision-Free Agentic Trajectories for Grounded Visual Perception
Authors:
Ashutosh Bajpai,
Tamal Majumder,
Akshay Nambi,
Tanmoy Chakraborty
Abstract:
Small Vision-Language Models (SVLMs) are efficient task controllers but often suffer from visual brittleness and poor tool orchestration. They typically require expensive supervised trajectory tuning to mitigate these deficits. In this work, we propose Self-supervised Perception Enabled by Cascaded Tool Rollout Alignment (SPECTRA), a supervision-free framework that bootstraps agentic capabilities…
▽ More
Small Vision-Language Models (SVLMs) are efficient task controllers but often suffer from visual brittleness and poor tool orchestration. They typically require expensive supervised trajectory tuning to mitigate these deficits. In this work, we propose Self-supervised Perception Enabled by Cascaded Tool Rollout Alignment (SPECTRA), a supervision-free framework that bootstraps agentic capabilities via Coldstart Reinforcement Learning for SVLMs. SPECTRA enforces Soft Structured Multi-turn Rollouts, a topological constraint that directs agents to explicitly sequence tool derived evidence before synthesis, effectively grounding reasoning in visual observations. We employ a multi-objective reward signal that simultaneously maximizes task correctness, rollout structure, and tool utility, enabling agent to self-discover robust behaviors without human preference labels. We further introduce Tool Instrumental Utility (TIU), a novel metric to quantify tool efficacy in the absence of ground truth. Extensive evaluations across composite and out-of-distribution (MMMU-Pro) benchmarks demonstrate that SPECTRA boosts agentic trajectories, improving task accuracy by up to 5% and tool efficiency by 9%, enabling more efficient multimodal agents that learn effectively from environmental interaction alone.
△ Less
Submitted 19 April, 2026;
originally announced April 2026.
-
SpatialMath: Spatial Comprehension-Infused Symbolic Reasoning for Mathematical Problem-Solving
Authors:
Ashutosh Bajpai,
Akshat Bhandari,
Akshay Nambi,
Tanmoy Chakraborty
Abstract:
Multimodal Small-to-Medium sized Language Models (MSLMs) have demonstrated strong capabilities in integrating visual and textual information but still face significant limitations in visual comprehension and mathematical reasoning, particularly in geometric problems with diverse levels of visual infusion. Current models struggle to accurately decompose intricate visual inputs and connect perceptio…
▽ More
Multimodal Small-to-Medium sized Language Models (MSLMs) have demonstrated strong capabilities in integrating visual and textual information but still face significant limitations in visual comprehension and mathematical reasoning, particularly in geometric problems with diverse levels of visual infusion. Current models struggle to accurately decompose intricate visual inputs and connect perception with structured reasoning, leading to suboptimal performance. To address these challenges, we propose SpatialMath, a novel Spatial Comprehension-Infused Symbolic Reasoning Framework designed to integrate spatial representations into structured symbolic reasoning chains. SpatialMath employs a specialized perception module to extract spatially-grounded representations from visual diagrams, capturing critical geometric structures and spatial relationships. These representations are then methodically infused into symbolic reasoning chains, facilitating visual comprehension-aware structured reasoning. To this end, we introduce MATHVERSE-PLUS, a novel dataset containing structured visual interpretations and step-by-step reasoning paths for vision-intensive mathematical problems. SpatialMath significantly outperforms strong multimodal baselines, achieving up to 10 percentage points improvement over supervised fine-tuning with data augmentation in vision-intensive settings. Robustness analysis reveals that enhanced spatial representations directly improve reasoning accuracy, reinforcing the need for structured perception-to-reasoning pipelines in MSLMs.
△ Less
Submitted 24 January, 2026;
originally announced January 2026.
-
Temporal Referential Consistency: Do LLMs Favor Sequences Over Absolute Time References?
Authors:
Ashutosh Bajpai,
Tanmoy Chakraborty
Abstract:
The increasing acceptance of large language models (LLMs) as an alternative to knowledge sources marks a significant paradigm shift across various domains, including time-sensitive fields such as law, healthcare, and finance. To fulfill this expanded role, LLMs must not only be factually accurate but also demonstrate consistency across temporal dimensions, necessitating robust temporal reasoning c…
▽ More
The increasing acceptance of large language models (LLMs) as an alternative to knowledge sources marks a significant paradigm shift across various domains, including time-sensitive fields such as law, healthcare, and finance. To fulfill this expanded role, LLMs must not only be factually accurate but also demonstrate consistency across temporal dimensions, necessitating robust temporal reasoning capabilities. Despite this critical requirement, efforts to ensure temporal consistency in LLMs remain scarce including noticeable absence of endeavors aimed at evaluating or augmenting LLMs across temporal references in time-sensitive inquiries. In this paper, we seek to address this gap by introducing a novel benchmark entitled temporal referential consistency, accompanied by a resource TEMP-ReCon designed to benchmark a wide range of both open-source and closed-source LLMs with various linguistic contexts characterized by differing resource richness (including English, French, and Romanian). The findings emphasis that LLMs do exhibit insufficient temporal referent consistency. To address this, we propose \newmodel, a reasoning path alignment-based model that aims to enhance the temporal referential consistency of LLMs. Our empirical experiments substantiate the efficacy of UnTRaP compared to several baseline models.
△ Less
Submitted 17 October, 2025;
originally announced October 2025.
-
Comparing Human and LLM Generated Code: The Jury is Still Out!
Authors:
Sherlock A. Licorish,
Ansh Bajpai,
Chetan Arora,
Fanyu Wang,
Kla Tantithamthavorn
Abstract:
Much is promised in relation to AI-supported software development. However, there has been limited evaluation effort in the research domain aimed at validating the true utility of such techniques, especially when compared to human coding outputs. We bridge this gap, where a benchmark dataset comprising 72 distinct software engineering tasks is used to compare the effectiveness of large language mo…
▽ More
Much is promised in relation to AI-supported software development. However, there has been limited evaluation effort in the research domain aimed at validating the true utility of such techniques, especially when compared to human coding outputs. We bridge this gap, where a benchmark dataset comprising 72 distinct software engineering tasks is used to compare the effectiveness of large language models (LLMs) and human programmers in producing Python software code. GPT-4 is used as a representative LLM, where for the code generated by humans and this LLM, we evaluate code quality and adherence to Python coding standards, code security and vulnerabilities, code complexity and functional correctness. We use various static analysis benchmarks, including Pylint, Radon, Bandit and test cases. Among the notable outcomes, results show that human-generated code recorded higher ratings for adhering to coding standards than GPT-4. We observe security flaws in code generated by both humans and GPT-4, however, code generated by humans shows a greater variety of problems, but GPT-4 code included more severe outliers. Our results show that although GPT-4 is capable of producing coding solutions, it frequently produces more complex code that may need more reworking to ensure maintainability. On the contrary however, our outcomes show that a higher number of test cases passed for code generated by GPT-4 across a range of tasks than code that was generated by humans. That said, GPT-4 frequently struggles with complex problem-solving that involve in-depth domain knowledge. This study highlights the potential utility of LLMs for supporting software development, however, tasks requiring comprehensive, innovative or unconventional solutions, and careful debugging and error correction seem to be better developed by human programmers. We plot an agenda for the software engineering community.
△ Less
Submitted 28 January, 2025;
originally announced January 2025.
-
Multilingual LLMs Inherently Reward In-Language Time-Sensitive Semantic Alignment for Low-Resource Languages
Authors:
Ashutosh Bajpai,
Tanmoy Chakraborty
Abstract:
The unwavering disparity in labeled resources between resource-rich languages and those considered low-resource remains a significant impediment for Large Language Models (LLMs). Recent strides in cross-lingual in-context learning (X-ICL), mainly through semantically aligned examples retrieved from multilingual pre-trained transformers, have shown promise in mitigating this issue. However, our inv…
▽ More
The unwavering disparity in labeled resources between resource-rich languages and those considered low-resource remains a significant impediment for Large Language Models (LLMs). Recent strides in cross-lingual in-context learning (X-ICL), mainly through semantically aligned examples retrieved from multilingual pre-trained transformers, have shown promise in mitigating this issue. However, our investigation reveals that LLMs intrinsically reward in-language semantically aligned cross-lingual instances over direct cross-lingual semantic alignments, with a pronounced disparity in handling time-sensitive queries in the X-ICL setup. Such queries demand sound temporal reasoning ability from LLMs, yet the advancements have predominantly focused on English. This study aims to bridge this gap by improving temporal reasoning capabilities in low-resource languages. To this end, we introduce mTEMPREASON, a temporal reasoning dataset aimed at the varied degrees of low-resource languages and propose Cross-Lingual Time-Sensitive Semantic Alignment (CLiTSSA), a novel method to improve temporal reasoning in these contexts. To facilitate this, we construct an extension of mTEMPREASON comprising pairs of parallel cross-language temporal queries along with their anticipated in-language semantic similarity scores. Our empirical evidence underscores the superior performance of CLiTSSA compared to established baselines across three languages -- Romanian, German, and French, encompassing three temporal tasks and including a diverse set of four contemporaneous LLMs. This marks a significant step forward in addressing resource disparity in the context of temporal reasoning across languages.
△ Less
Submitted 24 February, 2025; v1 submitted 10 December, 2024;
originally announced December 2024.
-
Temporally Consistent Factuality Probing for Large Language Models
Authors:
Ashutosh Bajpai,
Aaryan Goyal,
Atif Anwer,
Tanmoy Chakraborty
Abstract:
The prolific use of Large Language Models (LLMs) as an alternate knowledge base requires them to be factually consistent, necessitating both correctness and consistency traits for paraphrased queries. Recently, significant attempts have been made to benchmark datasets and metrics to evaluate LLMs for these traits. However, structural simplicity (subject-relation-object) and contemporary associatio…
▽ More
The prolific use of Large Language Models (LLMs) as an alternate knowledge base requires them to be factually consistent, necessitating both correctness and consistency traits for paraphrased queries. Recently, significant attempts have been made to benchmark datasets and metrics to evaluate LLMs for these traits. However, structural simplicity (subject-relation-object) and contemporary association in their query formulation limit the broader definition of factuality and consistency. In this study, we introduce TeCFaP, a novel Temporally Consistent Factuality Probe task to expand the consistent factuality probe in the temporal dimension. To this end, we propose TEMP-COFAC, a high-quality dataset of prefix-style English query paraphrases. Subsequently, we extend the definitions of existing metrics to represent consistent factuality across temporal dimension. We experiment with a diverse set of LLMs and find most of them performing poorly on TeCFaP. Next, we propose a novel solution CoTSeLF (Consistent-Time-Sensitive Learning Framework) combining multi-task instruction tuning (MT-IT) with consistent-time-sensitive reinforcement learning (CTSRL) to improve temporally consistent factuality in LLMs. Our experiments demonstrate the efficacy of CoTSeLF over several baselines.
△ Less
Submitted 17 October, 2024; v1 submitted 21 September, 2024;
originally announced September 2024.
-
Attire-Based Anomaly Detection in Restricted Areas Using YOLOv8 for Enhanced CCTV Security
Authors:
Abdul Aziz A. B,
Aindri Bajpai
Abstract:
This research introduces an innovative security enhancement approach, employing advanced image analysis and soft computing. The focus is on an intelligent surveillance system that detects unauthorized individuals in restricted areas by analyzing attire. Traditional security measures face challenges in monitoring unauthorized access. Leveraging YOLOv8, an advanced object detection algorithm, our sy…
▽ More
This research introduces an innovative security enhancement approach, employing advanced image analysis and soft computing. The focus is on an intelligent surveillance system that detects unauthorized individuals in restricted areas by analyzing attire. Traditional security measures face challenges in monitoring unauthorized access. Leveraging YOLOv8, an advanced object detection algorithm, our system identifies authorized personnel based on their attire in CCTV footage. The methodology involves training the YOLOv8 model on a comprehensive dataset of uniform patterns, ensuring precise recognition in specific regions. Soft computing techniques enhance adaptability to dynamic environments and varying lighting conditions. This research contributes to image analysis and soft computing, providing a sophisticated security solution. Emphasizing uniform-based anomaly detection, it establishes a foundation for robust security systems in restricted areas. The outcomes highlight the potential of YOLOv8-based surveillance in ensuring safety in sensitive locations.
△ Less
Submitted 4 January, 2026; v1 submitted 31 March, 2024;
originally announced April 2024.
-
Predicting suicidal behavior among Indian adults using childhood trauma, mental health questionnaires and machine learning cascade ensembles
Authors:
Akash K Rao,
Gunjan Y Trivedi,
Riri G Trivedi,
Anshika Bajpai,
Gajraj Singh Chauhan,
Vishnu K Menon,
Kathirvel Soundappan,
Hemalatha Ramani,
Neha Pandya,
Varun Dutt
Abstract:
Among young adults, suicide is India's leading cause of death, accounting for an alarming national suicide rate of around 16%. In recent years, machine learning algorithms have emerged to predict suicidal behavior using various behavioral traits. But to date, the efficacy of machine learning algorithms in predicting suicidal behavior in the Indian context has not been explored in literature. In th…
▽ More
Among young adults, suicide is India's leading cause of death, accounting for an alarming national suicide rate of around 16%. In recent years, machine learning algorithms have emerged to predict suicidal behavior using various behavioral traits. But to date, the efficacy of machine learning algorithms in predicting suicidal behavior in the Indian context has not been explored in literature. In this study, different machine learning algorithms and ensembles were developed to predict suicide behavior based on childhood trauma, different mental health parameters, and other behavioral factors. The dataset was acquired from 391 individuals from a wellness center in India. Information regarding their childhood trauma, psychological wellness, and other mental health issues was acquired through standardized questionnaires. Results revealed that cascade ensemble learning methods using a support vector machine, decision trees, and random forest were able to classify suicidal behavior with an accuracy of 95.04% using data from childhood trauma and mental health questionnaires. The study highlights the potential of using these machine learning ensembles to identify individuals with suicidal tendencies so that targeted interinterventions could be provided efficiently.
△ Less
Submitted 31 January, 2024;
originally announced January 2024.
-
Focal Inferential Infusion Coupled with Tractable Density Discrimination for Implicit Hate Detection
Authors:
Sarah Masud,
Ashutosh Bajpai,
Tanmoy Chakraborty
Abstract:
Although pretrained large language models (PLMs) have achieved state-of-the-art on many natural language processing (NLP) tasks, they lack an understanding of subtle expressions of implicit hate speech. Various attempts have been made to enhance the detection of implicit hate by augmenting external context or enforcing label separation via distance-based metrics. Combining these two approaches, we…
▽ More
Although pretrained large language models (PLMs) have achieved state-of-the-art on many natural language processing (NLP) tasks, they lack an understanding of subtle expressions of implicit hate speech. Various attempts have been made to enhance the detection of implicit hate by augmenting external context or enforcing label separation via distance-based metrics. Combining these two approaches, we introduce FiADD, a novel Focused Inferential Adaptive Density Discrimination framework. FiADD enhances the PLM finetuning pipeline by bringing the surface form/meaning of an implicit hate speech closer to its implied form while increasing the inter-cluster distance among various labels. We test FiADD on three implicit hate datasets and observe significant improvement in the two-way and three-way hate classification tasks. We further experiment on the generalizability of FiADD on three other tasks, detecting sarcasm, irony, and stance, in which surface and implied forms differ, and observe similar performance improvements. Consequently, we analyze the generated latent space to understand its evolution under FiADD, which corroborates the advantage of employing FiADD for implicit hate speech detection.
△ Less
Submitted 10 November, 2024; v1 submitted 21 September, 2023;
originally announced September 2023.
-
A Comparative Analysis of Techniques and Algorithms for Recognising Sign Language
Authors:
Rupesh Kumar,
Ayush Sinha,
Ashutosh Bajpai,
S. K Singh
Abstract:
Sign language is a visual language that enhances communication between people and is frequently used as the primary form of communication by people with hearing loss. Even so, not many people with hearing loss use sign language, and they frequently experience social isolation. Therefore, it is necessary to create human-computer interface systems that can offer hearing-impaired people a social plat…
▽ More
Sign language is a visual language that enhances communication between people and is frequently used as the primary form of communication by people with hearing loss. Even so, not many people with hearing loss use sign language, and they frequently experience social isolation. Therefore, it is necessary to create human-computer interface systems that can offer hearing-impaired people a social platform. Most commercial sign language translation systems now on the market are sensor-based, pricey, and challenging to use. Although vision-based systems are desperately needed, they must first overcome several challenges. Earlier continuous sign language recognition techniques used hidden Markov models, which have a limited ability to include temporal information. To get over these restrictions, several machine learning approaches are being applied to transform hand and sign language motions into spoken or written language. In this study, we compare various deep learning techniques for recognising sign language. Our survey aims to provide a comprehensive overview of the most recent approaches and challenges in this field.
△ Less
Submitted 24 May, 2023; v1 submitted 5 May, 2023;
originally announced May 2023.
-
Mediapipe and CNNs for Real-Time ASL Gesture Recognition
Authors:
Rupesh Kumar,
Ashutosh Bajpai,
Ayush Sinha
Abstract:
This research paper describes a realtime system for identifying American Sign Language (ASL) movements that employs modern computer vision and machine learning approaches. The suggested method makes use of the Mediapipe library for feature extraction and a Convolutional Neural Network (CNN) for ASL gesture classification. The testing results show that the suggested system can detect all ASL alphab…
▽ More
This research paper describes a realtime system for identifying American Sign Language (ASL) movements that employs modern computer vision and machine learning approaches. The suggested method makes use of the Mediapipe library for feature extraction and a Convolutional Neural Network (CNN) for ASL gesture classification. The testing results show that the suggested system can detect all ASL alphabets with an accuracy of 99.95%, indicating its potential for use in communication devices for people with hearing impairments. The proposed approach can also be applied to additional sign languages with similar hand motions, potentially increasing the quality of life for people with hearing loss. Overall, the study demonstrates the effectiveness of using Mediapipe and CNN for real-time sign language recognition, making a significant contribution to the field of computer vision and machine learning.
△ Less
Submitted 24 May, 2023; v1 submitted 9 May, 2023;
originally announced May 2023.
-
Symbolic Network: Generalized Neural Policies for Relational MDPs
Authors:
Sankalp Garg,
Aniket Bajpai,
Mausam
Abstract:
A Relational Markov Decision Process (RMDP) is a first-order representation to express all instances of a single probabilistic planning domain with possibly unbounded number of objects. Early work in RMDPs outputs generalized (instance-independent) first-order policies or value functions as a means to solve all instances of a domain at once. Unfortunately, this line of work met with limited succes…
▽ More
A Relational Markov Decision Process (RMDP) is a first-order representation to express all instances of a single probabilistic planning domain with possibly unbounded number of objects. Early work in RMDPs outputs generalized (instance-independent) first-order policies or value functions as a means to solve all instances of a domain at once. Unfortunately, this line of work met with limited success due to inherent limitations of the representation space used in such policies or value functions. Can neural models provide the missing link by easily representing more complex generalized policies, thus making them effective on all instances of a given domain?
We present SymNet, the first neural approach for solving RMDPs that are expressed in the probabilistic planning language of RDDL. SymNet trains a set of shared parameters for an RDDL domain using training instances from that domain. For each instance, SymNet first converts it to an instance graph and then uses relational neural models to compute node embeddings. It then scores each ground action as a function over the first-order action symbols and node embeddings related to the action. Given a new test instance from the same domain, SymNet architecture with pre-trained parameters scores each ground action and chooses the best action. This can be accomplished in a single forward pass without any retraining on the test instance, thus implicitly representing a neural generalized policy for the whole domain. Our experiments on nine RDDL domains from IPPC demonstrate that SymNet policies are significantly better than random and sometimes even more effective than training a state-of-the-art deep reactive policy from scratch.
△ Less
Submitted 29 June, 2020; v1 submitted 18 February, 2020;
originally announced February 2020.
-
Rural wireless deployments in India
Authors:
Arpit Bajpai
Abstract:
The Internet provides access to communications, information and opportunity to people. Growth of technology and its benefits should penetrate down to every citizen of a country. Rural Areas without Internet access risk being left behind in the information age. To be competitive, they must have broad and sustainable Internet services. Internet connectivity is especially important in developing coun…
▽ More
The Internet provides access to communications, information and opportunity to people. Growth of technology and its benefits should penetrate down to every citizen of a country. Rural Areas without Internet access risk being left behind in the information age. To be competitive, they must have broad and sustainable Internet services. Internet connectivity is especially important in developing countries like India where 67% of the population hail from rural areas. It is clear that most developing countries have still basic problems such as education, poverty, housing, and health, which are sure priorities for any government, it is important to determine whether an advanced informational infrastructure provides a tool for economic and social development. There are a lot of challenges that need to be considered while providing connectivity to rural areas such as high cost of installations, a dearth of skilled labor, deficiency of reliable power sources, local cooperation and support, etc. In this paper, we would like to discuss various dimensions and infrastructures in order to establish connectivity in the rural parts of India. We would also focus on the importance of maintenance of these wireless deployments and how it can be achieved.
△ Less
Submitted 4 September, 2019;
originally announced September 2019.
-
Size Independent Neural Transfer for RDDL Planning
Authors:
Sankalp Garg,
Aniket Bajpai,
Mausam
Abstract:
Neural planners for RDDL MDPs produce deep reactive policies in an offline fashion. These scale well with large domains, but are sample inefficient and time-consuming to train from scratch for each new problem. To mitigate this, recent work has studied neural transfer learning, so that a generic planner trained on other problems of the same domain can rapidly transfer to a new problem. However, th…
▽ More
Neural planners for RDDL MDPs produce deep reactive policies in an offline fashion. These scale well with large domains, but are sample inefficient and time-consuming to train from scratch for each new problem. To mitigate this, recent work has studied neural transfer learning, so that a generic planner trained on other problems of the same domain can rapidly transfer to a new problem. However, this approach only transfers across problems of the same size. We present the first method for neural transfer of RDDL MDPs that can transfer across problems of different sizes. Our architecture has two key innovations to achieve size independence: (1) a state encoder, which outputs a fixed length state embedding by max pooling over varying number of object embeddings, (2) a single parameter-tied action decoder that projects object embeddings into action probabilities for the final policy. On the two challenging RDDL domains of SysAdmin and Game Of Life, our approach powerfully transfers across problem sizes and has superior learning curves over training from scratch.
△ Less
Submitted 4 April, 2019; v1 submitted 8 February, 2019;
originally announced February 2019.
-
Transfer of Deep Reactive Policies for MDP Planning
Authors:
Aniket Bajpai,
Sankalp Garg,
Mausam
Abstract:
Domain-independent probabilistic planners input an MDP description in a factored representation language such as PPDDL or RDDL, and exploit the specifics of the representation for faster planning. Traditional algorithms operate on each problem instance independently, and good methods for transferring experience from policies of other instances of a domain to a new instance do not exist. Recently,…
▽ More
Domain-independent probabilistic planners input an MDP description in a factored representation language such as PPDDL or RDDL, and exploit the specifics of the representation for faster planning. Traditional algorithms operate on each problem instance independently, and good methods for transferring experience from policies of other instances of a domain to a new instance do not exist. Recently, researchers have begun exploring the use of deep reactive policies, trained via deep reinforcement learning (RL), for MDP planning domains. One advantage of deep reactive policies is that they are more amenable to transfer learning.
In this paper, we present the first domain-independent transfer algorithm for MDP planning domains expressed in an RDDL representation. Our architecture exploits the symbolic state configuration and transition function of the domain (available via RDDL) to learn a shared embedding space for states and state-action pairs for all problem instances of a domain. We then learn an RL agent in the embedding space, making a near zero-shot transfer possible, i.e., without much training on the new instance, and without using the domain simulator at all. Experiments on three different benchmark domains underscore the value of our transfer algorithm. Compared against planning from scratch, and a state-of-the-art RL transfer algorithm, our transfer solution has significantly superior learning curves.
△ Less
Submitted 26 October, 2018;
originally announced October 2018.