arXiv research

New algorithm reduces regret by allowing free exploration in multi-armed bandits.

New approach for reward-free exploration reduces estimation error.

Study reward-free RL in non-linear settings, improving efficiency and removing assumptions.

We study an exploration method for model-free RL that generalizes the counter-based exploration bonus methods and takes into account long term exploratory value of actions rather than a single step look-ahead. We propose a model-free RL method that modifies Delayed Q-learning and utilizes the long-term exploration bonu…

Maximizes Rényi entropy for efficient exploration in reward-free RL.

A single policy suffices for near-optimal parallel exploration in RL.

New model-free algorithms learn representations for low-rank MDPs efficiently.

New algorithm for RL with horizon-free reward-free exploration for linear MDPs.

Paper shows intrinsic motivation boosts exploration efficiency in HRL.

New RL method explores environments without rewards, achieving efficient policy generation.

New approach incentivizes strategic agents to explore, making exploration almost free.

Safe exploration in RF-RL doesn't increase sample complexity.

Q-Ensembles are a model-free approach where input images are fed into different Q-networks and exploration is driven by the assumption that uncertainty is proportional to the variance of the output Q-values obtained. They have been shown to perform relatively well compared to other exploration strategies. Further, mode…

The inference of correlated signal fields with unknown correlation structures is of high scientific and technological relevance, but poses significant conceptual and numerical challenges. To address these, we develop the correlated signal inference (CSI) algorithm within information field theory (IFT) and discuss its n…

Bayesian approach improves $\varepsilon$-greedy exploration in RL.

New algorithms allocate sampling budget to estimate group means without exploration.

Efficient Reinforcement Learning usually takes advantage of demonstration or good exploration strategy. By applying posterior sampling in model-free RL under the hypothesis of GP, we propose Gaussian Process Posterior Sampling Reinforcement Learning(GPPSTD) algorithm in continuous state space, giving theoretical justif…

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

Model-free reinforcement learning methods such as the Proximal Policy Optimization algorithm (PPO) have successfully applied in complex decision-making problems such as Atari games. However, these methods suffer from high variances and high sample complexity. On the other hand, model-based reinforcement learning method…

A new framework isolates exploration challenges in RL without explicit rewards.

Algorithm achieves optimal pricing with minimal exploration for dynamic markets.

How to best explore in domains with sparse, delayed, and deceptive rewards is an important open problem for reinforcement learning (RL). This paper considers one such domain, the recently-proposed multi-agent benchmark of Pommerman. This domain is very challenging for RL --- past work has shown that model-free RL algor…

RandQL is a new model-free algorithm for MDPs with a novel learning rate randomization approach.

New algorithm for reward-free RL with linear function approximation, reducing sample complexity.

Free lunch from noise reveals linear spectral features for RL.

A new model-free algorithm achieves near-optimal regret for infinite-horizon MDPs.

New $L_1$-Coverage objective simplifies exploration in reinforcement learning.

Random exploration optimizes Bayesian optimization with optimal error rates and computational efficiency.

The contextual bandit literature has traditionally focused on algorithms that address the exploration-exploitation tradeoff. In particular, greedy algorithms that exploit current estimates without any exploration may be sub-optimal in general. However, exploration-free greedy algorithms are desirable in practical setti…

Active inference enhances RL by balancing exploration and exploitation.

Study finds optimal retirement timing in uncertain wage scenarios.

New strategies avoid forced exploration for unimodal bandits.

Reward-free RL in linear MDPs is as hard as reward-aware RL.

We define risk-free portfolios using three gauge invariant differential operators that require such portfolios to be insensitive to price changes, to be self-financing, and to produce a zero real return so there are no risk-free profits. This definition identifies the risk-free rate as the return of an infinitely diver…

A new approach for deep exploration in sparse reward reinforcement learning.

Study on random knot diagrams and their probability of forming specific knots.

We study the sample complexity of model-based reinforcement learning (henceforth RL) in general contextual decision processes that require strategic exploration to find a near-optimal policy. We design new algorithms for RL with a generic model class and analyze their statistical properties. Our algorithms have sample …

Eigenoptions improve credit assignment in reinforcement learning.

Proposes Optimistic Pessimistically Initialised Q-Learning (OPIQ) for better exploration in RL.

Research in reinforcement learning has produced algorithms for optimal decision making under uncertainty that fall within two main types. The first employs a Bayesian framework, where optimality improves with increased computational time. This is because the resulting planning task takes the form of a dynamic programmi…

New RL algorithm reduces deployment cost for linear function approximations.

PC-PG balances exploration and exploitation in reinforcement learning.

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…

Paper improves sample complexity for reward-free RL in low-rank MDPs.

The study finds stably free modules and distinct 2-complexes for large ranks.

New algorithm learns optimal policies without explicit rewards.

This study proposes hidden state curiosity to enhance RL models' resilience against noise.

Paper proposes efficient sample collection strategy for RL.