arXiv research

New IRL algorithm identifies optimal reward and policy from expert demonstrations.

Paper proposes operator deep Q-learning for quick reward adaptation.

Method distills reward and strategies from diverse demonstrators.

VASE uses Bayesian neural networks to improve exploration in sparse reward environments.

Study on deep neural networks for reward modeling with pairwise comparison data.

Reverse Experience Replay improves Deep Q-learning for sparse rewards.

This work provides a thorough study on how reward scaling can affect performance of deep reinforcement learning agents. In particular, we would like to answer the question that how does reward scaling affect non-saturating ReLU networks in RL? This question matters because ReLU is one of the most effective activation f…

NeuralRBMLE tackles explore-exploit trade-offs in contextual bandits with neural networks.

SA-GFN corrects biases in GFlowNets due to graph symmetries.

Capsule Networks improve autonomous navigation in sparse environments.

Reinforcement learning is concerned with identifying reward-maximizing behaviour policies in environments that are initially unknown. State-of-the-art reinforcement learning approaches, such as deep Q-networks, are model-free and learn to act effectively across a wide range of environments such as Atari games, but requ…

Generative Flow Networks use submodular upper bounds to generate more data.

To solve complex real-world problems with reinforcement learning, we cannot rely on manually specified reward functions. Instead, we can have humans communicate an objective to the agent directly. In this work, we combine two approaches to learning from human feedback: expert demonstrations and trajectory preferences. …

OP-GFNs sample candidates in order-preserving proportion to a learned reward function.

Develops neural network framework for risk-reward optimization problems.

Proposes EE-Net for neural exploration in contextual bandits.

NeuralUCB tackles contextual bandits with neural networks and UCB for near-optimal regret.

We introduce a method by which a generative model learning the joint distribution between actions and future states can be used to automatically infer a control scheme for any desired reward function, which may be altered on the fly without retraining the model. In this method, the problem of action selection is reduce…

A new algorithm for offline RL with trajectory-wise reward reduces bias and variance errors.

Recent reinforcement learning (RL) approaches have shown strong performance in complex domains such as Atari games, but are often highly sample inefficient. A common approach to reduce interaction time with the environment is to use reward shaping, which involves carefully designing reward functions that provide the ag…

This paper presents a new neural architecture that combines a modulated Hebbian network (MOHN) with DQN, which we call modulated Hebbian plus Q network architecture (MOHQA). The hypothesis is that such a combination allows MOHQA to solve difficult partially observable Markov decision process (POMDP) problems which impa…

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…

New algorithm uses GNNs to optimize rewards in graph-structured data.

Algorithm learns user's reward function from hypothetical behaviors.

A network of spiking agents learns complex tasks using global reward signals.

In structured output prediction tasks, labeling ground-truth training output is often expensive. However, for many tasks, even when the true output is unknown, we can evaluate predictions using a scalar reward function, which may be easily assembled from human knowledge or non-differentiable pipelines. But searching th…

This paper improves sample efficiency for off-policy evaluation with preference data.

BatchGFN uses generative flow networks for efficient batch active learning.

Enhanced financial reward with shuffled feature CNN-DRL.

This paper proposes a new algorithm for learning guidance rewards in RL.

In classical Q-learning, the objective is to maximize the sum of discounted rewards through iteratively using the Bellman equation as an update, in an attempt to estimate the action value function of the optimal policy. Conventionally, the loss function is defined as the temporal difference between the action value and…

Local search improves GFlowNets' ability to generate high-reward samples.

Complex networks are often either too large for full exploration, partially accessible, or partially observed. Downstream learning tasks on these incomplete networks can produce low quality results. In addition, reducing the incompleteness of the network can be costly and nontrivial. As a result, network discovery algo…

A new method recovers rewards from behavior policies using classification and regression.

Reinforcement learning is a promising framework for solving control problems, but its use in practical situations is hampered by the fact that reward functions are often difficult to engineer. Specifying goals and tasks for autonomous machines, such as robots, is a significant challenge: conventionally, reward function…

We consider a problem of learning the reward and policy from expert examples under unknown dynamics. Our proposed method builds on the framework of generative adversarial networks and introduces the empowerment-regularized maximum-entropy inverse reinforcement learning to learn near-optimal rewards and policies. Empowe…

We propose Deep Q-Networks (DQN) with model-based exploration, an algorithm combining both model-free and model-based approaches that explores better and learns environments with sparse rewards more efficiently. DQN is a general-purpose, model-free algorithm and has been proven to perform well in a variety of tasks inc…

PFN-TS uses Thompson sampling with PFNs to improve contextual bandit performance.

Paper uses deep reinforcement learning for cryptocurrency market making.

Boosted GFlowNets improve exploration by sequentially training GFlowNets with residual rewards.

Meta-learning curiosity algorithms improves exploration across various tasks.

The study analyzes how neural reward models learn features for policy optimization in a Gaussian single-index model.

System learns optimizer hyperparameters to generalize across tasks.

Improves text-to-image diffusion models using GFlowNets.

This work uses model uncertainty for efficient exploration in sparse reward environments.

New framework for efficient query-based imitation learning.

New strategies improve multi-agent decision-making on irregular networks.

Exploration efficiency is a challenging problem in multi-agent reinforcement learning (MARL), as the policy learned by confederate MARL depends on the collaborative approach among multiple agents. Another important problem is the less informative reward restricts the learning speed of MARL compared with the informative…