Search Results for author:
Found 55 papers, 15 papers with code
A2Perf: Real-World Autonomous Agents Benchmark
However, there is a lack of benchmarking suites that define the environments, datasets, and metrics which can be used to provide a meaningful way for the community to compare progress on applying these methods to real-world problems.
Inference-Aware Fine-Tuning for Best-of-N Sampling in Large Language Models
Recent studies have indicated that effectively utilizing inference-time compute is crucial for attaining better performance from large language models (LLMs).
Improving Dynamic Object Interactions in Text-to-Video Generation with AI Feedback
In this work, we investigate the use of feedback to enhance the object dynamics in text-to-video models.
ElasticTok: Adaptive Tokenization for Image and Video
Efficient video tokenization remains a key bottleneck in learning general purpose vision models that are capable of processing long video sequences.
Training Language Models to Self-Correct via Reinforcement Learning
In particular, we observe that training via SFT falls prey to either a distribution mismatch between mistakes made by the data-collection policy and the model's own responses, or to behavior collapse, where learning implicitly prefers only a certain mode of correction behavior that is often not effective at self-correction on test problems.
Geometric-Averaged Preference Optimization for Soft Preference Labels
In this work, we introduce the distributional soft preference labels and improve Direct Preference Optimization (DPO) with a weighted geometric average of the LLM output likelihood in the loss function.
Many-Shot In-Context Learning
We find that both Reinforced and Unsupervised ICL can be quite effective in the many-shot regime, particularly on complex reasoning tasks.
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
In this report, we introduce the Gemini 1. 5 family of models, representing the next generation of highly compute-efficient multimodal models capable of recalling and reasoning over fine-grained information from millions of tokens of context, including multiple long documents and hours of video and audio.
Stop Regressing: Training Value Functions via Classification for Scalable Deep RL
Observing this discrepancy, in this paper, we investigate whether the scalability of deep RL can also be improved simply by using classification in place of regression for training value functions.
Guided Evolution with Binary Discriminators for ML Program Search
How to automatically design better machine learning programs is an open problem within AutoML.
Exposing Limitations of Language Model Agents in Sequential-Task Compositions on the Web
We show that while existing prompted LMAs (gpt-3. 5-turbo or gpt-4) achieve 94. 0% average success rate on base tasks, their performance degrades to 24. 9% success rate on compositional tasks.
Levels of AGI for Operationalizing Progress on the Path to AGI
We propose a framework for classifying the capabilities and behavior of Artificial General Intelligence (AGI) models and their precursors.
A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis
Pre-trained large language models (LLMs) have recently achieved better generalization and sample efficiency in autonomous web automation.
Ranked #1 on
on Mind2Web
Personality Traits in Large Language Models
The advent of large language models (LLMs) has revolutionized natural language processing, enabling the generation of coherent and contextually relevant human-like text.
ArchGym: An Open-Source Gymnasium for Machine Learning Assisted Architecture Design
The ease of data collection and aggregation in ArchGym facilitates research in ML-aided architecture design space exploration.
Multimodal Web Navigation with Instruction-Finetuned Foundation Models
The progress of autonomous web navigation has been hindered by the dependence on billions of exploratory interactions via online reinforcement learning, and domain-specific model designs that make it difficult to leverage generalization from rich out-of-domain data.
Multi-Agent Reachability Calibration with Conformal Prediction
We investigate methods to provide safety assurances for autonomous agents that incorporate predictions of other, uncontrolled agents' behavior into their own trajectory planning.
Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarios
To our knowledge, this is the first application of a combined imitation and reinforcement learning approach in autonomous driving that utilizes large amounts of real-world human driving data.
Multi-Agent Reinforcement Learning for Microprocessor Design Space Exploration
It is unclear how scalable single-agent formulations are as we increase the complexity of the design space (e. g., full stack System-on-Chip design).
CLUTR: Curriculum Learning via Unsupervised Task Representation Learning
Recently, Unsupervised Environment Design (UED) emerged as a new paradigm for zero-shot generalization by simultaneously learning a task distribution and agent policies on the generated tasks.
Understanding HTML with Large Language Models
We contribute HTML understanding models (fine-tuned LLMs) and an in-depth analysis of their capabilities under three tasks: (i) Semantic Classification of HTML elements, (ii) Description Generation for HTML inputs, and (iii) Autonomous Web Navigation of HTML pages.
Fast Inference and Transfer of Compositional Task Structures for Few-shot Task Generalization
Different from the previous meta-rl methods trying to directly infer the unstructured task embedding, our multi-task subtask graph inferencer (MTSGI) first infers the common high-level task structure in terms of the subtask graph from the training tasks, and use it as a prior to improve the task inference in testing.
Hierarchical Reinforcement Learning
Meta Reinforcement Learning
+3
Tiny Robot Learning: Challenges and Directions for Machine Learning in Resource-Constrained Robots
Machine learning (ML) has become a pervasive tool across computing systems.
Evolving Pareto-Optimal Actor-Critic Algorithms for Generalizability and Stability
Generalizability and stability are two key objectives for operating reinforcement learning (RL) agents in the real world.
Environment Generation for Zero-Shot Compositional Reinforcement Learning
We learn to generate environments composed of multiple pages or rooms, and train RL agents capable of completing wide-range of complex tasks in those environments.
Automated Reinforcement Learning (AutoRL): A Survey and Open Problems
The combination of Reinforcement Learning (RL) with deep learning has led to a series of impressive feats, with many believing (deep) RL provides a path towards generally capable agents.
Compositional Learning-based Planning for Vision POMDPs
The Partially Observable Markov Decision Process (POMDP) is a powerful framework for capturing decision-making problems that involve state and transition uncertainty.
Less is More: Generating Grounded Navigation Instructions from Landmarks
We study the automatic generation of navigation instructions from 360-degree images captured on indoor routes.
Targeted Environment Design from Offline Data
We formalize our approach as offline targeted environment design(OTED), which automatically learns a distribution over simulator parameters to match a provided offline dataset, and then uses the learned simulator to train an RL agent in standard online fashion.
Multi-Task Learning with Sequence-Conditioned Transporter Networks
Enabling robots to solve multiple manipulation tasks has a wide range of industrial applications.
SparseDice: Imitation Learning for Temporally Sparse Data via Regularization
We are concerned with a setting where the demonstrations comprise only a subset of state-action pairs (as opposed to the whole trajectories).
Differentiable Architecture Search for Reinforcement Learning
In this paper, we investigate the fundamental question: To what extent are gradient-based neural architecture search (NAS) techniques applicable to RL?
Joint Attention for Multi-Agent Coordination and Social Learning
We then train agents to minimize the difference between the attention weights that they apply to the environment at each timestep, and the attention of other agents.
Adversarial Environment Generation for Learning to Navigate the Web
The regret objective trains the adversary to design a curriculum of environments that are "just-the-right-challenge" for the navigator agents; our results show that over time, the adversary learns to generate increasingly complex web navigation tasks.
AutoPilot: Automating SoC Design Space Exploration for SWaP Constrained Autonomous UAVs
Balancing a computing system for a UAV requires considering both the cyber (e. g., sensor rate, compute performance) and physical (e. g., payload weight) characteristics that affect overall performance.
Evolving Reinforcement Learning Algorithms
Learning from scratch on simple classical control and gridworld tasks, our method rediscovers the temporal-difference (TD) algorithm.
Visual Navigation Among Humans with Optimal Control as a Supervisor
Videos describing our approach and experiments, as well as a demo of HumANav are available on the project website.
Model-based Reinforcement Learning for Decentralized Multiagent Rendezvous
We propose hierarchical predictive planning (HPP), a model-based reinforcement learning method for decentralized multiagent rendezvous.
Neural Collision Clearance Estimator for Batched Motion Planning
We present a neural network collision checking heuristic, ClearanceNet, and a planning algorithm, CN-RRT.
Learned Critical Probabilistic Roadmaps for Robotic Motion Planning
Critical PRMs are demonstrated to achieve up to three orders of magnitude improvement over uniform sampling, while preserving the guarantees and complexity of sampling-based motion planning.
QuaRL: Quantization for Fast and Environmentally Sustainable Reinforcement Learning
We believe that this is the first of many future works on enabling computationally energy-efficient and sustainable reinforcement learning.
Zero-shot Imitation Learning from Demonstrations for Legged Robot Visual Navigation
Here, we propose a zero-shot imitation learning approach for training a visual navigation policy on legged robots from human (third-person perspective) demonstrations, enabling high-quality navigation and cost-effective data collection.
Learning to Seek: Autonomous Source Seeking with Deep Reinforcement Learning Onboard a Nano Drone Microcontroller
We present fully autonomous source seeking onboard a highly constrained nano quadcopter, by contributing application-specific system and observation feature design to enable inference of a deep-RL policy onboard a nano quadcopter.
Safe Policy Learning for Continuous Control
We study continuous action reinforcement learning problems in which it is crucial that the agent interacts with the environment only through safe policies, i. e.,~policies that keep the agent in desirable situations, both during training and at convergence.
RL-RRT: Kinodynamic Motion Planning via Learning Reachability Estimators from RL Policies
Through the combination of sampling-based planning, a Rapidly Exploring Randomized Tree (RRT) and an efficient kinodynamic motion planner through machine learning, we propose an efficient solution to long-range planning for kinodynamic motion planning.
Air Learning: A Deep Reinforcement Learning Gym for Autonomous Aerial Robot Visual Navigation
We find that the trajectories on an embedded Ras-Pi are vastly different from those predicted on a high-end desktop system, resulting in up to 40% longer trajectories in one of the environments.
Evolving Rewards to Automate Reinforcement Learning
Many continuous control tasks have easily formulated objectives, yet using them directly as a reward in reinforcement learning (RL) leads to suboptimal policies.
Long-Range Indoor Navigation with PRM-RL
Long-range indoor navigation requires guiding robots with noisy sensors and controls through cluttered environments along paths that span a variety of buildings.
Lyapunov-based Safe Policy Optimization for Continuous Control
We formulate these problems as constrained Markov decision processes (CMDPs) and present safe policy optimization algorithms that are based on a Lyapunov approach to solve them.
Learning to Navigate the Web
Even though recent approaches improve the success rate on relatively simple environments with the help of human demonstrations to guide the exploration, they still fail in environments where the set of possible instructions can reach millions.
Learning Navigation Behaviors End-to-End with AutoRL
The policies are trained in small, static environments with AutoRL, an evolutionary automation layer around Reinforcement Learning (RL) that searches for a deep RL reward and neural network architecture with large-scale hyper-parameter optimization.
Resilient Computing with Reinforcement Learning on a Dynamical System: Case Study in Sorting
Robots and autonomous agents often complete goal-based tasks with limited resources, relying on imperfect models and sensor measurements.
MPDCompress - Matrix Permutation Decomposition Algorithm for Deep Neural Network Compression
Deep neural networks (DNNs) have become the state-of-the-art technique for machine learning tasks in various applications.
Deep Neural Networks for Swept Volume Prediction Between Configurations
Swept Volume (SV), the volume displaced by an object when it is moving along a trajectory, is considered a useful metric for motion planning.
PRM-RL: Long-range Robotic Navigation Tasks by Combining Reinforcement Learning and Sampling-based Planning
The RL agents learn short-range, point-to-point navigation policies that capture robot dynamics and task constraints without knowledge of the large-scale topology.
