Search Results for author:
Found 33 papers, 13 papers with code
Provable Interactive Learning with Hindsight Instruction Feedback
We study interactive learning in a setting where the agent has to generate a response (e. g., an action or trajectory) given a context and an instruction.
Dataset Reset Policy Optimization for RLHF
Motivated by the fact that offline preference dataset provides informative states (i. e., data that is preferred by the labelers), our new algorithm, Dataset Reset Policy Optimization (DR-PO), integrates the existing offline preference dataset into the online policy training procedure via dataset reset: it directly resets the policy optimizer to the states in the offline dataset, instead of always starting from the initial state distribution.
Towards Principled Representation Learning from Videos for Reinforcement Learning
We study two types of settings: one where there is iid noise in the observation, and a more challenging setting where there is also the presence of exogenous noise, which is non-iid noise that is temporally correlated, such as the motion of people or cars in the background.
Policy Improvement using Language Feedback Models
We introduce Language Feedback Models (LFMs) that identify desirable behaviour - actions that help achieve tasks specified in the instruction - for imitation learning in instruction following.
The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction
Transformer-based Large Language Models (LLMs) have become a fixture in modern machine learning.
LLF-Bench: Benchmark for Interactive Learning from Language Feedback
We introduce a new benchmark, LLF-Bench (Learning from Language Feedback Benchmark; pronounced as "elf-bench"), to evaluate the ability of AI agents to interactively learn from natural language feedback and instructions.
Learning to Generate Better Than Your LLM
In particular, we extend RL algorithms to allow them to interact with a dynamic black-box guide LLM and propose RL with guided feedback (RLGF), a suite of RL algorithms for LLM fine-tuning.
Towards Data-Driven Offline Simulations for Online Reinforcement Learning
Modern decision-making systems, from robots to web recommendation engines, are expected to adapt: to user preferences, changing circumstances or even new tasks.
Agent-Controller Representations: Principled Offline RL with Rich Exogenous Information
We find that contemporary representation learning techniques can fail on datasets where the noise is a complex and time dependent process, which is prevalent in practical applications.
Provable Safe Reinforcement Learning with Binary Feedback
Many existing approaches to safe RL rely on receiving numeric safety feedback, but in many cases this feedback can only take binary values; that is, whether an action in a given state is safe or unsafe.
Guaranteed Discovery of Control-Endogenous Latent States with Multi-Step Inverse Models
In many sequential decision-making tasks, the agent is not able to model the full complexity of the world, which consists of multitudes of relevant and irrelevant information.
Sample-Efficient Reinforcement Learning in the Presence of Exogenous Information
In real-world reinforcement learning applications the learner's observation space is ubiquitously high-dimensional with both relevant and irrelevant information about the task at hand.
Provably Sample-Efficient RL with Side Information about Latent Dynamics
We study reinforcement learning (RL) in settings where observations are high-dimensional, but where an RL agent has access to abstract knowledge about the structure of the state space, as is the case, for example, when a robot is tasked to go to a specific room in a building using observations from its own camera, while having access to the floor plan.
Understanding Contrastive Learning Requires Incorporating Inductive Biases
Contrastive learning is a popular form of self-supervised learning that encourages augmentations (views) of the same input to have more similar representations compared to augmentations of different inputs.
Provable RL with Exogenous Distractors via Multistep Inverse Dynamics
We initiate the formal study of latent state discovery in the presence of such exogenous noise sources by proposing a new model, the Exogenous Block MDP (EX-BMDP), for rich observation RL.
Provably Filtering Exogenous Distractors using Multistep Inverse Dynamics
We initiate the formal study of latent state discovery in the presence of such exogenous noise sources by proposing a new model, the Exogenous Block MDP (EX-BMDP), for rich observation RL.
Investigating the Role of Negatives in Contrastive Representation Learning
We focus on disambiguating the role of one of these parameters: the number of negative examples.
Have you tried Neural Topic Models? Comparative Analysis of Neural and Non-Neural Topic Models with Application to COVID-19 Twitter Data
Topic models are widely used in studying social phenomena.
Interactive Learning from Activity Description
We present a novel interactive learning protocol that enables training request-fulfilling agents by verbally describing their activities.
General Reinforcement Learning
Grounded language learning
+2
Provable Rich Observation Reinforcement Learning with Combinatorial Latent States
We propose a novel setting for reinforcement learning that combines two common real-world difficulties: presence of observations (such as camera images) and factored states (such as location of objects).
Learning the Linear Quadratic Regulator from Nonlinear Observations
We introduce a new algorithm, RichID, which learns a near-optimal policy for the RichLQR with sample complexity scaling only with the dimension of the latent state space and the capacity of the decoder function class.
Kinematic State Abstraction and Provably Efficient Rich-Observation Reinforcement Learning
We present an algorithm, HOMER, for exploration and reinforcement learning in rich observation environments that are summarizable by an unknown latent state space.
Combating the Compounding-Error Problem with a Multi-step Model
In this paper, we address the compounding-error problem by introducing a multi-step model that directly outputs the outcome of executing a sequence of actions.
Model-based Reinforcement Learning
reinforcement-learning
+1
Touchdown: Natural Language Navigation and Spatial Reasoning in Visual Street Environments
We study the problem of jointly reasoning about language and vision through a navigation and spatial reasoning task.
Ranked #10 on
Vision and Language Navigation
on Touchdown Dataset
Early Fusion for Goal Directed Robotic Vision
Building perceptual systems for robotics which perform well under tight computational budgets requires novel architectures which rethink the traditional computer vision pipeline.
Mapping Navigation Instructions to Continuous Control Actions with Position-Visitation Prediction
We propose an approach for mapping natural language instructions and raw observations to continuous control of a quadcopter drone.
Towards a Simple Approach to Multi-step Model-based Reinforcement Learning
When environmental interaction is expensive, model-based reinforcement learning offers a solution by planning ahead and avoiding costly mistakes.
Model-based Reinforcement Learning
reinforcement-learning
+1
Policy Shaping and Generalized Update Equations for Semantic Parsing from Denotations
Semantic parsing from denotations faces two key challenges in model training: (1) given only the denotations (e. g., answers), search for good candidate semantic parses, and (2) choose the best model update algorithm.
Mapping Instructions to Actions in 3D Environments with Visual Goal Prediction
We propose to decompose instruction execution to goal prediction and action generation.
Equivalence Between Wasserstein and Value-Aware Loss for Model-based Reinforcement Learning
Learning a generative model is a key component of model-based reinforcement learning.
Model-based Reinforcement Learning
reinforcement-learning
+1
Lipschitz Continuity in Model-based Reinforcement Learning
We go on to prove an error bound for the value-function estimate arising from Lipschitz models and show that the estimated value function is itself Lipschitz.
Model-based Reinforcement Learning
reinforcement-learning
+1
CHALET: Cornell House Agent Learning Environment
We present CHALET, a 3D house simulator with support for navigation and manipulation.
Mapping Instructions and Visual Observations to Actions with Reinforcement Learning
We propose to directly map raw visual observations and text input to actions for instruction execution.
