Q-Learning

380 papers with code • 0 benchmarks • 2 datasets

The goal of Q-learning is to learn a policy, which tells an agent what action to take under what circumstances.

( Image credit: Playing Atari with Deep Reinforcement Learning )

Libraries

Use these libraries to find Q-Learning models and implementations
6 papers
2,399
6 papers
31
5 papers
383
See all 29 libraries.

Ensembling Prioritized Hybrid Policies for Multi-agent Pathfinding

ai4co/eph-mapf 12 Mar 2024

We first propose a selective communication block to gather richer information for better agent coordination within multi-agent environments and train the model with a Q-learning-based algorithm.

8
12 Mar 2024

Scalable Online Exploration via Coverability

philip-amortila/l1-coverability 11 Mar 2024

We propose exploration objectives -- policy optimization objectives that enable downstream maximization of any reward function -- as a conceptual framework to systematize the study of exploration.

0
11 Mar 2024

Belief-Enriched Pessimistic Q-Learning against Adversarial State Perturbations

sliencerx/belief-enriched-robust-q-learning 6 Mar 2024

Existing solutions either introduce a regularization term to improve the smoothness of the trained policy against perturbations or alternatively train the agent's policy and the attacker's policy.

2
06 Mar 2024

Efficient Episodic Memory Utilization of Cooperative Multi-Agent Reinforcement Learning

hyunghona/emu 2 Mar 2024

To address this, we introduce Efficient episodic Memory Utilization (EMU) for MARL, with two primary objectives: (a) accelerating reinforcement learning by leveraging semantically coherent memory from an episodic buffer and (b) selectively promoting desirable transitions to prevent local convergence.

10
02 Mar 2024

Leveraging Digital Cousins for Ensemble Q-Learning in Large-Scale Wireless Networks

talhabozkus/digital-cousins-for-ensemble-q-learning 12 Feb 2024

Herein, a novel ensemble Q-learning algorithm that addresses the performance and complexity challenges of the traditional Q-learning algorithm for optimizing wireless networks is presented.

0
12 Feb 2024

Multi-Timescale Ensemble Q-learning for Markov Decision Process Policy Optimization

talhabozkus/tsp_23_supplementary_file 8 Feb 2024

Reinforcement learning (RL) is a classical tool to solve network control or policy optimization problems in unknown environments.

0
08 Feb 2024

RadDQN: a Deep Q Learning-based Architecture for Finding Time-efficient Minimum Radiation Exposure Pathway

biswajitsadhu/raddqn 1 Feb 2024

However, the lack of efficient reward function and effective exploration strategy thwarted its implementation in the development of radiation-aware autonomous unmanned aerial vehicle (UAV) for achieving maximum radiation protection.

3
01 Feb 2024

VQC-Based Reinforcement Learning with Data Re-uploading: Performance and Trainability

rodrigocoelho7/vqc_qlearning 21 Jan 2024

This work empirically studies the performance and trainability of such VQC-based Deep Q-Learning models in classic control benchmark environments.

1
21 Jan 2024

Decision Making in Non-Stationary Environments with Policy-Augmented Search

scope-lab-vu/PAMCTS 6 Jan 2024

In this paper, we introduce \textit{Policy-Augmented Monte Carlo tree search} (PA-MCTS), which combines action-value estimates from an out-of-date policy with an online search using an up-to-date model of the environment.

4
06 Jan 2024

SPQR: Controlling Q-ensemble Independence with Spiked Random Model for Reinforcement Learning

dohyeoklee/SPQR NeurIPS 2023

Alleviating overestimation bias is a critical challenge for deep reinforcement learning to achieve successful performance on more complex tasks or offline datasets containing out-of-distribution data.

2
06 Jan 2024