Amy Zhang

Zero-Shot Constraint Satisfaction with Forward- Backward Representations

Adriana Hugessen

Cyrus Neary

Traditionally, constrained policy optimization with Reinforcement Learning (RL) requires learning a new policy from scratch for any new envi… (see more)ronment, goal or cost function, with limited generalization to new tasks and constraints. Given the sample inefficiency of many common deep RL methods, this procedure can be impractical for many real-world scenarios, particularly when constraints or tasks are changing. As an alternative, in the unconstrained setting, various works have sought to pre-train representations from offline datasets to accelerate policy optimization upon specification of a reward. Such methods can permit faster adaptation to new tasks in a given environment, dramatically improving sample efficiency. Recently, zero-shot policy optimization has been explored by leveraging a particular

2025-07-01

rl-conference.cc/RLC/2025/Workshop/RLBrew (published)

openreview.net

MaestroMotif: Skill Design from Artificial Intelligence Feedback

Martin Klissarov

Mikael Henaff

Roberta Raileanu

Marlos C. Machado

Describing skills in natural language has the potential to provide an accessible way to inject human knowledge about decision-making into an… (see more) AI system. We present MaestroMotif, a method for AI-assisted skill design, which yields high-performing and adaptable agents. MaestroMotif leverages the capabilities of Large Language Models (LLMs) to effectively create and reuse skills. It first uses an LLM's feedback to automatically design rewards corresponding to each skill, starting from their natural language description. Then, it employs an LLM's code generation abilities, together with reinforcement learning, for training the skills and combining them to implement complex behaviors specified in language. We evaluate MaestroMotif using a suite of complex tasks in the NetHack Learning Environment (NLE), demonstrating that it surpasses existing approaches in both performance and usability.

2025-01-22

ICLR.cc/2025/Conference (oral)

doi.org

openreview.net

Towards General-Purpose Model-Free Reinforcement Learning

Yuandong Tian

Reinforcement learning (RL) promises a framework for near-universal problem-solving. In practice however, RL algorithms are often tailored t… (see more)o specific benchmarks, relying on carefully tuned hyperparameters and algorithmic choices. Recently, powerful model-based RL methods have shown impressive general results across benchmarks but come at the cost of increased complexity and slow run times, limiting their broader applicability. In this paper, we attempt to find a unifying model-free deep RL algorithm that can address a diverse class of domains and problem settings. To achieve this, we leverage model-based representations that approximately linearize the value function, taking advantage of the denser task objectives used by model-based RL while avoiding the costs associated with planning or simulated trajectories. We evaluate our algorithm, MR.Q, on a variety of common RL benchmarks with a single set of hyperparameters and show a competitive performance against domain-specific and general baselines, providing a concrete step towards building general-purpose model-free deep RL algorithms.

2025-01-22

ICLR.cc/2025/Conference (spotlight)

doi.org

openreview.net

MaestroMotif: Skill Design from Artificial Intelligence Feedback

Martin Klissarov

Mikael Henaff

Roberta Raileanu

Marlos C. Machado

Describing skills in natural language has the potential to provide an accessible way to inject human knowledge about decision-making into an… (see more) AI system. We present MaestroMotif, a method for AI-assisted skill design, which yields high-performing and adaptable agents. MaestroMotif leverages the capabilities of Large Language Models (LLMs) to effectively create and reuse skills. It first uses an LLM's feedback to automatically design rewards corresponding to each skill, starting from their natural language description. Then, it employs an LLM's code generation abilities, together with reinforcement learning, for training the skills and combining them to implement complex behaviors specified in language. We evaluate MaestroMotif using a suite of complex tasks in the NetHack Learning Environment (NLE), demonstrating that it surpasses existing approaches in both performance and usability.

2024-12-11

ArXiv (preprint)

doi.org

arxiv.org

MaestroMotif: Skill Design from Artificial Intelligence Feedback

Martin Klissarov

Mikael Henaff

Roberta Raileanu

Marlos C. Machado

Describing skills in natural language has the potential to provide an accessible way to inject human knowledge about decision-making into an… (see more) AI system. We present MaestroMotif, a method for AI-assisted skill design, which yields high-performing and adaptable agents. MaestroMotif leverages the capabilities of Large Language Models (LLMs) to effectively create and reuse skills. It first uses an LLM's feedback to automatically design rewards corresponding to each skill, starting from their natural language description. Then, it employs an LLM's code generation abilities, together with reinforcement learning, for training the skills and combining them to implement complex behaviors specified in language. We evaluate MaestroMotif using a suite of complex tasks in the NetHack Learning Environment (NLE), demonstrating that it surpasses existing approaches in both performance and usability.

2024-12-11

ArXiv (preprint)

arxiv.org

Efficient Reinforcement Learning by Discovering Neural Pathways

Samin Yeasar Arnob

Riyasat Ohib

Sergey Plis

Amy Zhang

Alessandro Sordoni

Doina Precup

Reinforcement learning (RL) algorithms have been very successful at tackling complex control problems, such as AlphaGo or fusion control. Ho… (see more)wever, current research mainly emphasizes solution quality, often achieved by using large models trained on large amounts of data, and does not account for the financial, environmental, and societal costs associated with developing and deploying such models. Modern neural networks are often overparameterized and a significant number of parameters can be pruned without meaningful loss in performance, resulting in more efficient use of the model's capacity lottery ticket. We present a methodology for identifying sub-networks within a larger network in reinforcement learning (RL). We call such sub-networks, neural pathways. We show empirically that even very small learned sub-networks, using less than 5% of the large network's parameters, can provide very good quality solutions. We also demonstrate the training of multiple pathways within the same networks in a multitask setup, where each pathway is encouraged to tackle a separate task. We evaluate empirically our approach on several continuous control tasks, in both online and offline training

2024-09-25

NeurIPS.cc/2024/Conference (poster)

openreview.net

Motif: Intrinsic Motivation from Artificial Intelligence Feedback

Roberta Raileanu

Mikael Henaff

Exploring rich environments and evaluating one's actions without prior knowledge is immensely challenging. In this paper, we propose Motif, … (see more)a general method to interface such prior knowledge from a Large Language Model (LLM) with an agent. Motif is based on the idea of grounding LLMs for decision-making without requiring them to interact with the environment: it elicits preferences from an LLM over pairs of captions to construct an intrinsic reward, which is then used to train agents with reinforcement learning. We evaluate Motif's performance and behavior on the challenging, open-ended and procedurally-generated NetHack game. Surprisingly, by only learning to maximize its intrinsic reward, Motif achieves a higher game score than an algorithm directly trained to maximize the score itself. When combining Motif's intrinsic reward with the environment reward, our method significantly outperforms existing approaches and makes progress on tasks where no advancements have ever been made without demonstrations. Finally, we show that Motif mostly generates intuitive human-aligned behaviors which can be steered easily through prompt modifications, while scaling well with the LLM size and the amount of information given in the prompt.

2024-01-16

ICLR.cc/2024/Conference (poster)

doi.org

openreview.net

A Model-Based Solution to the Offline Multi-Agent Reinforcement Learning Coordination Problem

Paul Barde

Jakob Nicolaus Foerster

Derek Nowrouzezahrai

Amy Zhang

2024-01-01

AAMAS (published)

doi.org

arxiv.org

Latent State Marginalization as a Low-cost Approach for Improving Exploration

Qinqing Zheng

Ricky T. Q. Chen

2023-02-01

ICLR.cc/2023/Conference (poster)

doi.org

openreview.net

Multitask Reinforcement Learning by Optimizing Neural Pathways

Samin Yeasar Arnob

Riyasat Ohib

Amy Zhang

Sergey Plis

Doina Precup

Reinforcement learning (RL) algorithms have achieved great success in learning specific tasks, as evidenced by examples such as AlphaGo or f… (see more)usion control. However, it is still difficult for an RL agent to learn how to solve multiple tasks. In this paper, we propose a novel multitask learning framework, in which multiple specialized pathways through a single network are trained simultaneously, with each pathway focusing on a single task. We show that this approach achieves competitive performance with existing multitask RL methods, while using only 5% of the number of neurons per task. We demonstrate empirically the success of our approach on several continuous control tasks, in both online and offline training.

2023-02-01

ICLR.cc/2023/Conference (rejected)

openreview.net

Latent State Marginalization as a Low-cost Approach for Improving Exploration

Qinqing Zheng

Ricky T. Q. Chen

While the maximum entropy (MaxEnt) reinforcement learning (RL) framework -- often touted for its exploration and robustness capabilities -- … (see more)is usually motivated from a probabilistic perspective, the use of deep probabilistic models has not gained much traction in practice due to their inherent complexity. In this work, we propose the adoption of latent variable policies within the MaxEnt framework, which we show can provably approximate any policy distribution, and additionally, naturally emerges under the use of world models with a latent belief state. We discuss why latent variable policies are difficult to train, how naive approaches can fail, then subsequently introduce a series of improvements centered around low-cost marginalization of the latent state, allowing us to make full use of the latent state at minimal additional cost. We instantiate our method under the actor-critic framework, marginalizing both the actor and critic. The resulting algorithm, referred to as Stochastic Marginal Actor-Critic (SMAC), is simple yet effective. We experimentally validate our method on continuous control tasks, showing that effective marginalization can lead to better exploration and more robust training. Our implementation is open sourced at https://github.com/zdhNarsil/Stochastic-Marginal-Actor-Critic.

2022-10-03

ArXiv (preprint)

doi.org

arxiv.org

Block Contextual MDPs for Continual Learning

Shagun Sodhani

Franziska Meier

Joelle Pineau

Amy Zhang

In reinforcement learning (RL), when defining a Markov Decision Process (MDP), the environment dynamics is implicitly assumed to be stationa… (see more)ry. This assumption of stationarity, while simplifying, can be unrealistic in many scenarios. In the continual reinforcement learning scenario, the sequence of tasks is another source of nonstationarity. In this work, we propose to examine this continual reinforcement learning setting through the Block Contextual MDP (BC-MDP) framework, which enables us to relax the assumption of stationarity. This framework challenges RL algorithms to handle both nonstationarity and rich observation settings and, by additionally leveraging smoothness properties, enables us to study generalization bounds for this setting. Finally, we take inspiration from adaptive control to propose a novel algorithm that addresses the challenges introduced by this more realistic BC-MDP setting, allows for zero-shot adaptation at evaluation time, and achieves strong performance on several nonstationary environments.

2022-05-11

Proceedings of The 4th Annual Learning for Dynamics and Control Conference (published)

proceedings.mlr.press

openreview.net

Custom AI Learning Programs

Mil'Haq Fest 2025

Mila Community of Practice

Supervision Requests

Publications

Custom AI Learning Programs

Mil'Haq Fest 2025

Mila Community of Practice

Supervision Requests

Popular keywords:

Amy Zhang

Publications