Deep Reinforcement Learning codes for study. Currently, there are only codes for algorithms: DQN, C51, QR-DQN, IQN, QUOTA.

[ICRA 2024] Decentralized Multi-Robot Navigation for Autonomous Surface Vehicles with Distributional Reinforcement Learning

[IROS 2023] Robust Unmanned Surface Vehicle Navigation with Distributional Reinforcement Learning

🐳 Implementation of various Distributional Reinforcement Learning Algorithms using TensorFlow2.

PyTorch implementation of the state-of-the-art distributional reinforcement learning algorithm Fully Parameterized Quantile Function (FQF) and Extensions: N-step Bootstrapping, PER, Noisy Layer, Dueling Networks, and parallelization.

[RA-L 2025] Distributional Reinforcement Learning Based Integrated Decision Making and Control for Autonomous Surface Vehicles

Implementation of some of the Deep Distributional Reinforcement Learning Algorithms.

PyTorch implementation of D4PG with the SOTA IQN Critic instead of C51. Implementation includes also the extensions Munchausen RL and D2RL which can be added to D4PG to improve its performance.

[UR 2023] Robust Route Planning with Distributional Reinforcement Learning in a Stochastic Road Network Environment

Deep reinforcement learning framework for fast prototyping based on PyTorch

DRL-Router is a method based on distributional reinforcement learning for RSP problem。

Reinforcement learning algorithm implementation

Distributional reinforcement learning algorithm using conjugated discrete distributions (C2D). Data and graphs for stochastic Atari 2600 environments.

Author implementation of DSUP(q) algorithms from the NeurIPS 2024 paper "Action Gaps and Advantages in Continuous-Time Distributional Reinforcement Learning"

Quantile Regression DQN implementation for bridge fleet maintenance optimization using Markov Decision Process. Migrated from C51 distributional RL (v0.8) with 200 quantiles and Huber loss. Features: Dueling architecture, Noisy Networks, PER, N-step learning. All 6 maintenance actions show positive returns with 68-78% VaR improvement.

Solving CartPole using Distributional RL

A comprehensive reinforcement learning system for pump equipment condition-based maintenance using DQN (Deep Q-Network) with quantile regression and aging factor integration.

No description provided.

Slide presentation reviewing advances in reinforcement learning

C51 Distributional DQN (v0.8) for bridge fleet maintenance optimization. Implements categorical return distributions (Bellemare et al., PMLR 2017) with 300x speedup via vectorized projection. Combines Noisy Networks, Dueling DQN, Double DQN, PER, and n-step learning. Validated on 200-bridge fleet: +3,173 reward in 83 min (25k episodes).

Example Categorical DQN implementation with ReLAx

Multi-Equipment CBM (Condition-Based Maintenance) optimization using Deep Q-Learning with cost leveling and scenario comparison. Advanced RL system with QR-DQN, N-step learning, and parallel environments for HVAC equipment predictive maintenance.

Multi-Equipment CBM system using QR-DQN with advanced probability distribution analysis. Coordinated maintenance decision-making for 4 industrial equipment units with realistic anomaly rates (1.9-2.2%), comprehensive risk analysis (VaR/CVaR), and 51-quantile distribution visualization.

A Reinforcement Learning MVP (Minimum Viable Product) for Condition-Based Maintenance (CBM) using industrial equipment temperature sensor data. This project implements a sophisticated QR-DQN (Quantile Regression Deep Q-Network) agent to learn optimal maintenance policies balancing risk mitigation and cost minimization.

Simple Implementations of RL Algorithm in PyTorch

Alternative (torch) author implementation of algorithms from the NeurIPS 2024 paper "Action Gaps and Advantages in Continuous-Time Distributional Reinforcement Learning"