Author name cluster

Deepeka Garg

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers

1 author row

AAMAS Conference 2026 Conference Paper

PADME: Procedure Aware DynaMic Execution

Deepeka Garg
Sihan Zeng
Annapoorani L. Narayanan
Sumitra Ganesh
Leo Ardon

Executing long-horizon procedures from natural language is challenging for LLM agents due to the lack of structure in free-form instructions like recipes or business workflows, often leading to execution drift or failure. We propose Procedure Aware DynaMic Execution (PADME), a framework that autonomously transforms procedural text into executable graphs capturing dependencies and decision logic. PADME employs a two-phase approach: a Teach phase for systematic structuring and an Execute phase for dynamic, realtime inputs and environment feedback-driven traversal. This graphbased representation provides an inductive bias that reduces error accumulation and ensures scalability. Empirically, PADME achieves state-of-the-art performance on four benchmarks, including ALF- World and ScienceWorld, demonstrating that agents equipped with graph-based procedure representations offer a powerful intermediate abstraction for robust and generalizable execution.

PDF

AAMAS Conference 2023 Conference Paper

Phantom - A RL-driven Multi-Agent Framework to Model Complex Systems

Leo Ardon
Jared Vann
Deepeka Garg
Thomas Spooner
Sumitra Ganesh

Agent based modeling (ABM) is a computational approach to modeling complex systems by specifying the behavior of autonomous decision-making components or agents in the system and allowing the system dynamics to emerge from their interactions. Recent advances in the field of Multi-agent reinforcement learning (MARL) have made it feasible to study the equilibrium of complex environments where multiple agents learn simultaneously. However, most ABM frameworks are not RL-native, in that they do not offer concepts and interfaces that are compatible with the use of MARL to learn agent behaviors. In this paper, we introduce a new open-source framework, Phantom, to bridge the gap between ABM and MARL. Phantom is an RL-driven framework for agent-based modeling of complex multi-agent systems including, but not limited to, economic systems, markets and auctions. The framework aims to provide the tools to simplify the ABM specification in a MARL-compatible way - including features to encode dynamic partial observability, agent utility functions, heterogeneity in agent preferences or types, and constraints on the order in which agents can act (e. g. Stackelberg games, or more complex turn-taking environments). In this paper, we present the main features of Phantom and their design rationale.

PDF

AAMAS Conference 2022 Conference Paper

Fully-Autonomous, Vision-based Traffic Signal Control: From Simulation to Reality

Deepeka Garg
Maria Chli
George Vogiatzis

Ineffective traffic signal control is one of the major causes of congestion in urban road networks. Dynamically changing traffic conditions and live traffic state estimation are fundamental challenges that limit the ability of the existing signal infrastructure in rendering individualized signal control in real-time. We use deep reinforcement learning (DRL) to address these challenges. Due to economic and safety constraints associated with training such agents in the real world, a practical approach is to do so in simulation before deployment. Domain randomisation is an effective technique for bridging the reality gap and ensuring effective transfer of simulation-trained agents to the real world. In this paper, we develop a fully-autonomous, vision-based DRL agent that achieves adaptive signal control in the face of complex, imprecise, and dynamic traffic environments. Our agent uses live visual data (i. e. a stream of real-time RGB footage) from an intersection to extensively perceive and subsequently act upon the traffic environment. Employing domain randomisation, we examine our agent’s generalisation capabilities under varying traffic conditions in both the simulation and the real-world environments. In a diverse validation set independent of training data, our traffic control agent reliably adapted to novel traffic situations and demonstrated a positive transfer to previously unseen real intersections despite being trained entirely in simulation.

PDF

AAMAS Conference 2019 Conference Paper

Traffic3D: A New Traffic Simulation Paradigm

Deepeka Garg
Maria Chli
George Vogiatzis

The field of Deep Reinforcement Learning has evolved significantly over the last few years. However, an important and not yet fullyattained goal is to produce intelligent agents which can be successfully taken out of the laboratory and employed in the real-world. Intelligent agents that are successfully deployable in real-world settings require substantial prior exposure to their intended environments. When this is not practical or possible, the agents benefit from being trained and tested on powerful test-beds, effectively replicating the real-world. To achieve traffic management at an unprecedented level of efficiency, in this work, we demonstrate a significantly richer new traffic simulation environment; Traffic3D, a platform to effectively simulate and evaluate a variety of 3D road traffic scenarios, closely mimicking real-world traffic characteristics, including faithful simulation of individual vehicle behavior, precise physics of movement and photo-realism. In addition to deep reinforcement learning, Traffic3D also facilitates research in several other domains such as imitation learning, learning by interaction, visual question answering, object detection and segmentation, unsupervised representation learning and procedural generation.

PDF