A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
OpenAI Five defeated Dota 2 champions using deep reinforcement learning.
We present the OpenAI Remote Rendering Backend (ORRB), a system that allows fast and customizable rendering of robotics environments. It is based on the Unity3d game engine and interfaces with the MuJoCo physics simulation library. ORRB was designed with visual domain randomization in mind. It is optimized for cloud de…
Proposes ABIDES-Gym for financial markets simulation.
Photonic quantum reinforcement learning for control problems.
Multi-agent Q-learning untangles braids, improving over training.
Jukebox generates high-fidelity songs with singing in raw audio.
RAD enhances RL algorithms with data augmentations.
A simple DQN-based multi-agent RL system for binary actions.
Simulates sepsis treatment decisions using a world model approach.
Tool converts industrial systems to RL environments for optimization.
Online random forests improve Q-learning performance in specific gym environments.
Study efficient convergence of RL algorithm with function approximation.
In this work, we focus on fine-tuning an OpenAI GPT-2 pre-trained model for generating patent claims. GPT-2 has demonstrated impressive efficacy of pre-trained language models on various tasks, particularly coherent text generation. Patent claim language itself has rarely been explored in the past and poses a unique ch…
MobILE learns from expert demonstrations without access to actions, achieving strong performance guarantees.
Randomly guessing weights helps analyze RL benchmarks objectively.
IDAC improves reinforcement learning efficiency by modeling implicit distributions.
The paper uses news headlines to predict stock prices using embeddings.
Paper improves reinforcement learning in multi-scene tasks.
Distributional reinforcement learning (distributional RL) has seen empirical success in complex Markov Decision Processes (MDPs) in the setting of nonlinear function approximation. However, there are many different ways in which one can leverage the distributional approach to reinforcement learning. In this paper, we p…
We present an open-source tool for visualizing multi-head self-attention in Transformer-based language representation models. The tool extends earlier work by visualizing attention at three levels of granularity: the attention-head level, the model level, and the neuron level. We describe how each of these views can he…
In this paper, we propose a dual memory structure for reinforcement learning algorithms with replay memory. The dual memory consists of a main memory that stores various data and a cache memory that manages the data and trains the reinforcement learning agent efficiently. Experimental results show that the dual memory …
This project combines recent advances in experience replay techniques, namely, Combined Experience Replay (CER), Prioritized Experience Replay (PER), and Hindsight Experience Replay (HER). We show the results of combinations of these techniques with DDPG and DQN methods. CER always adds the most recent experience to th…
A new method for estimating joint value functions in multi-scene reinforcement learning.
WAPPO optimizes feature distributions for better visual transfer in RL.
In this paper, the method UCB-RS, which resorts to recommendation system (RS) for enhancing the upper-confidence bound algorithm UCB, is presented. The proposed method is used for dealing with non-stationary and large-state spaces multi-armed bandit problems. The proposed method has been targeted to the problem of the …
Flow-based generative models (Dinh et al., 2014) are conceptually attractive due to tractability of the exact log-likelihood, tractability of exact latent-variable inference, and parallelizability of both training and synthesis. In this paper we propose Glow, a simple type of generative flow using an invertible 1x1 con…
Reproducibility in reinforcement learning is challenging: uncontrolled stochasticity from many sources, such as the learning algorithm, the learned policy, and the environment itself have led researchers to report the performance of learned agents using aggregate metrics of performance over multiple random seeds for a …
Policy optimization on high-dimensional continuous control tasks exhibits its difficulty caused by the large variance of the policy gradient estimators. We present the action subspace dependent gradient (ASDG) estimator which incorporates the Rao-Blackwell theorem (RB) and Control Variates (CV) into a unified framework…
Paper proposes a new RL approach combining IL and RL methods to improve decision-making.
A new algorithm reduces memory usage for long token attention in streaming applications.
In value-based reinforcement learning methods such as deep Q-learning, function approximation errors are known to lead to overestimated value estimates and suboptimal policies. We show that this problem persists in an actor-critic setting and propose novel mechanisms to minimize its effects on both the actor and the cr…
Deep active inference learns policies from sensory inputs.
CoNES optimizes blackbox functions using convex optimization and information geometry.
We use reinforcement learning (RL) to learn dexterous in-hand manipulation policies which can perform vision-based object reorientation on a physical Shadow Dexterous Hand. The training is performed in a simulated environment in which we randomize many of the physical properties of the system like friction coefficients…
Financial institutions face new model risks with AI, requiring enhanced model risk management.
Zap Q-learning is a recent class of reinforcement learning algorithms, motivated primarily as a means to accelerate convergence. Stability theory has been absent outside of two restrictive classes: the tabular setting, and optimal stopping. This paper introduces a new framework for analysis of a more general class of r…
Deep reinforcement learning has shown its success in game playing. However, 2.5D fighting games would be a challenging task to handle due to ambiguity in visual appearances like height or depth of the characters. Moreover, actions in such games typically involve particular sequential action orders, which also makes the…
Develops a simple model to understand learning curves for arbitrary power laws.
We study risk-sensitive imitation learning where the agent's goal is to perform at least as well as the expert in terms of a risk profile. We first formulate our risk-sensitive imitation learning setting. We consider the generative adversarial approach to imitation learning (GAIL) and derive an optimization problem for…
Deep Reinforcement Learning has enabled the control of increasingly complex and high-dimensional problems. However, the need of vast amounts of data before reasonable performance is attained prevents its widespread application. We employ binary corrective feedback as a general and intuitive manner to incorporate human …
We demonstrate that models trained only in simulation can be used to solve a manipulation problem of unprecedented complexity on a real robot. This is made possible by two key components: a novel algorithm, which we call automatic domain randomization (ADR) and a robot platform built for machine learning. ADR automatic…
ChatGPT launch boosted AI-related crypto assets by 10.7% to 15.6%.
The General Video Game AI (GVGAI) competition and its associated software framework provides a way of benchmarking AI algorithms on a large number of games written in a domain-specific description language. While the competition has seen plenty of interest, it has so far focused on online planning, providing a forward …
PixelCNNs are a recently proposed class of powerful generative models with tractable likelihood. Here we discuss our implementation of PixelCNNs which we make available at https://github.com/openai/pixel-cnn. Our implementation contains a number of modifications to the original model that both simplify its structure an…
Improved DDPMs achieve high log-likelihoods and sample quality with fewer passes.
Reinforcement learning usually makes use of numerical rewards, which have nice properties but also come with drawbacks and difficulties. Using rewards on an ordinal scale (ordinal rewards) is an alternative to numerical rewards that has received more attention in recent years. In this paper, a general approach to adapt…
We propose a general formulation for addressing reinforcement learning (RL) problems in settings with observational data. That is, we consider the problem of learning good policies solely from historical data in which unobserved factors (confounders) affect both observed actions and rewards. Our formulation allows us t…
The ever-growing volume of data of user-generated content on social media provides a nearly unlimited corpus of unlabeled data even in languages where resources are scarce. In this paper, we demonstrate that state-of-the-art results on two Thai social text categorization tasks can be realized by pretraining a language …