arXiv research

A novel framework uses goal-conditioned reinforcement learning to generate diverse samples.

Framework for multi-agent RL with human feedback in a Snake game.

Unified policy controls diverse agents through modular neural networks.

Algorithm learns to switch control among agents in a team.

Task-agnostic RL tackles exploration in MDPs with multiple tasks.

New federated learning protocols improve on knowledge distillation's poor performance.

DAC-SSM learns domain-agnostic states for better imitation learning.

This paper proposes a new method to connect language and physical actions in reinforcement learning.

Catastrophic forgetting is the notorious vulnerability of neural networks to the change of the data distribution while learning. This phenomenon has long been considered a major obstacle for allowing the use of learning agents in realistic continual learning settings. A large body of continual learning research assumes…

Proposes a new theoretical framework for PbRL that requires less human feedback.

Generically learns movement control policies from exploration data.

CODA resolves coordination issues in offline multi-agent reinforcement learning.

While model-based deep reinforcement learning (RL) holds great promise for sample efficiency and generalization, learning an accurate dynamics model is often challenging and requires substantial interaction with the environment. A wide variety of domains have dynamics that share common foundations like the laws of clas…

Inverse reinforcement learning (IRL) enables an agent to learn complex behavior by observing demonstrations from a (near-)optimal policy. The typical assumption is that the learner's goal is to match the teacher's demonstrated behavior. In this paper, we consider the setting where the learner has its own preferences th…

RADIAL-RL improves deep RL agents' robustness against adversarial attacks.

MANGA transfers policies across environments with varying dynamics and noise.

We consider a scenario where an agent has multiple available strategies to explore an unknown environment. For each new interaction with the environment, the agent must select which exploration strategy to use. We provide a new strategy-agnostic method that treat the situation as a Multi-Armed Bandits problem where the…

PeL separates sensory interface optimization from decision learning.

This paper optimizes model-based RL for two-player zero-sum games with near-optimal sample complexity.

We propose a method for tackling catastrophic forgetting in deep reinforcement learning that is \textit{agnostic} to the timescale of changes in the distribution of experiences, does not require knowledge of task boundaries, and can adapt in \textit{continuously} changing environments. In our \textit{policy consolidati…

The composition of elementary behaviors to solve challenging transfer learning problems is one of the key elements in building intelligent machines. To date, there has been plenty of work on learning task-specific policies or skills but almost no focus on composing necessary, task-agnostic skills to find a solution to …

CUDC collects diverse data for offline RL by predicting future states.

A multi-agent system improves crypto portfolio management by processing diverse data types.

E-valuator converts verifier scores into reliable decision rules.

Traditional reinforcement learning agents learn from experience, past or present, gained through interaction with their environment. Our approach synthesizes experience, without requiring an agent to interact with their environment, by asking the policy directly "Are there situations X, Y, and Z, such that in these sit…

Efficient exploration is an unsolved problem in Reinforcement Learning which is usually addressed by reactively rewarding the agent for fortuitously encountering novel situations. This paper introduces an efficient active exploration algorithm, Model-Based Active eXploration (MAX), which uses an ensemble of forward mod…

New method handles unknown task boundaries in continual learning.

Optimizes bidding strategies for LinkedIn ads across multiple platforms.

This study uses DRL to hedge American put options, outperforming traditional methods.

While recent progress has spawned very powerful machine learning systems, those agents remain extremely specialized and fail to transfer the knowledge they gain to similar yet unseen tasks. In this paper, we study a simple reinforcement learning problem and focus on learning policies that encode the proper invariances …

New algorithm matches best regret bound for tabular Contextual Bandit problems.

Event-based learning reduces communication in distributed networks.

Fractal neural networks play SimCity and Conway's Game of Life on varying scales.

RL learns to ignore factors in factor investing portfolios.

Adaptive Bayesian learning agent for non-stationary bandits.

JPS improves joint policies for multi-agent collaboration in imperfect information games.

Developed an explainable DRL model for financial portfolio management.

Our research is focused on understanding and applying biological memory transfers to new AI systems that can fundamentally improve their performance, throughout their fielded lifetime experience. We leverage current understanding of biological memory transfer to arrive at AI algorithms for memory consolidation and repl…

Paper proposes a policy-search algorithm to learn entropy-maximizing exploration policies in reward-free environments.

Deep RL learns effective job shop scheduling rules from raw features.

New method evaluates AI stock prediction systems based on decision-making processes.

We consider tackling a single-agent RL problem by distributing it to $n$ learners. These learners, called advisors, endeavour to solve the problem from a different focus. Their advice, taking the form of action values, is then communicated to an aggregator, which is in control of the system. We show that the local plan…

Study uses agent-based simulation to analyze impact of OBI strategy on financial markets.

First proper learning algorithm for Gaussian halfspaces with matching sample and computational complexity.

When learning behavior, training data is often generated by the learner itself; this can result in unstable training dynamics, and this problem has particularly important applications in safety-sensitive real-world control tasks such as robotics. In this work, we propose a principled and model-agnostic approach to miti…

This paper introduces CENIE to quantify environment novelty for better UED.

Improved cooperation between levels boosts reinforcement learning performance.

Building an open-domain conversational agent is a challenging problem. Current evaluation methods, mostly post-hoc judgments of static conversation, do not capture conversation quality in a realistic interactive context. In this paper, we investigate interactive human evaluation and provide evidence for its necessity; …