arXiv research

Novelty search in low-dimensional space improves sample efficiency in exploration tasks.

Proposes EVE for efficient exploration in reinforcement learning.

HOMER learns latent states to explore rich environments efficiently.

Efficient exploration improves large language model performance with fewer queries.

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

Recently deep reinforcement learning (DRL) has achieved outstanding success on solving many difficult and large-scale RL problems. However the high sample cost required for effective learning often makes DRL unaffordable in resource-limited applications. With the aim of improving sample efficiency and learning performa…

Paper shows intrinsic motivation boosts exploration efficiency in HRL.

Efficient exploration is one of the key challenges for reinforcement learning (RL) algorithms. Most traditional sample efficiency bounds require strategic exploration. Recently many deep RL algorithms with simple heuristic exploration strategies that have few formal guarantees, achieve surprising success in many domain…

Maximize to Explore integrates RL components for efficient policy discovery.

MPPO improves exploration efficiency for on-policy methods.

A fundamental issue in reinforcement learning algorithms is the balance between exploration of the environment and exploitation of information already obtained by the agent. Especially, exploration has played a critical role for both efficiency and efficacy of the learning process. However, Existing works for explorati…

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

This paper shows how diverse tasks can make inefficient exploration in MTRL efficient.

MAME models a separate exploration policy for faster adaptation.

ASE safely explores unknown MDPs with unknown dynamics, improving sample efficiency.

Hyper addresses the hyperparameter tuning challenge in RL, improving exploration efficiency and robustness.

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…

Efficient exploration in complex environments remains a major challenge for reinforcement learning. We propose bootstrapped DQN, a simple algorithm that explores in a computationally and statistically efficient manner through use of randomized value functions. Unlike dithering strategies such as epsilon-greedy explorat…

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

DAC enhances exploration in reinforcement learning with entropy regularization.

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…

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

New framework uses unsupervised learning for efficient exploration in RL.

Efficient exploration is necessary to achieve good sample efficiency for reinforcement learning in general. From small, tabular settings such as gridworlds to large, continuous and sparse reward settings such as robotic object manipulation tasks, exploration through adding an uncertainty bonus to the reward function ha…

We propose randomized least-squares value iteration (RLSVI) -- a new reinforcement learning algorithm designed to explore and generalize efficiently via linearly parameterized value functions. We explain why versions of least-squares value iteration that use Boltzmann or epsilon-greedy exploration can be highly ineffic…

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…

Our work is a simple extension of the paper "Exploration by Random Network Distillation". More in detail, we show how to efficiently combine Intrinsic Rewards with Experience Replay in order to achieve more efficient and robust exploration (with respect to PPO/RND) and consequently better results in terms of agent perf…

MADE improves exploration in RL by maximizing deviation from explored regions.

New methods for efficient exploration under unknown linear constraints in bandits.

Bayesian method improves reinforcement learning efficiency by encouraging exploration.

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

Plan2Explore learns new tasks efficiently through self-supervised planning.

We study the use of randomized value functions to guide deep exploration in reinforcement learning. This offers an elegant means for synthesizing statistically and computationally efficient exploration with common practical approaches to value function learning. We present several reinforcement learning algorithms that…

Latent variable models improve RL by facilitating efficient learning and exploration.

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

Paper presents an efficient exploration method for reinforcement learning.

SUPE combines unlabeled data with RL to efficiently explore tasks.

We present a new algorithm that significantly improves the efficiency of exploration for deep Q-learning agents in dialogue systems. Our agents explore via Thompson sampling, drawing Monte Carlo samples from a Bayes-by-Backprop neural network. Our algorithm learns much faster than common exploration strategies such as …

CAE repurposes critics for efficient exploration in RL.

Effective and intelligent exploration has been an unresolved problem for reinforcement learning. Most contemporary reinforcement learning relies on simple heuristic strategies such as $ε$-greedy exploration or adding Gaussian noise to actions. These heuristics, however, are unable to intelligently distinguish the well …

Novel meta-RL strategy improves efficiency in learning novel tasks.

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

Paper explores BERT's efficiency on SQuAD2.0, freezing layers and using adapters.

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

ACE improves GFlowNet exploration efficiency by balancing complementary search strategies.

HyperX uses reward bonuses to enable efficient exploration in meta-learning.

OPPO optimizes policy learning with provable efficiency.

New algorithms for efficient learning with partial information, reducing regret.