rl-benchmark

Here are 5 public repositories matching this topic...

tk-yasuno / markov-dqn-v07-noisy

Markov Decision Process DQN with Noisy Networks for Exploration (ICLR 2018) - 21.1% performance improvement over ε-greedy.

reinforcement-learning dqn deep-q-learning noisy-networks exploration-strategy markov-decision-process efficient-exploration sample-efficiency disaster-resilience performance-improvement rl-benchmark infrastructure-prognostics

Updated Dec 8, 2025
Python

igopalakrishna / sbsim

Star

Google Open-Source Project: Stochastic building simulator and real-world dataset for training and benchmarking reinforcement learning agents in energy-efficient smart control environments. Built with Gym, TensorFlow Agents, and 6+ years of real building data.

python docker reinforcement-learning openai-gym dataset energy-efficiency gym-environment smart-building occupancy-model smart-control building-simulation tensorflow-agents offline-rl climate-tech rl-benchmark

Updated Jan 30, 2026
Python

Tahernezhad / Deep-Q-Learning-Workbench

Star

Clean, modular DQN in PyTorch with Double/Dueling options and MLP/CNN/LSTM backbones—plug-and-play for Gymnasium environments.

deep-reinforcement-learning openai-gym pytorch lstm reinforcement-learning-algorithms mlp gymnasium deep-q-learning pytho double-dqn dueling-dqn lunar-lander replay-buffer dq cnn1d double-deep-q-learning rl-benchmark

Updated Sep 23, 2025
Python

mansoor-mamnoon / offline-rl-agent

Star

Offline RL benchmark project featuring a custom Gym environment, dual observation modes, reward shaping, and real-time PyGame rendering

docker reinforcement-learning inference pytorch neural-networks pruning cql quantization gymnasium model-compression custom-environment offline-rl observation-space td3-bc rl-benchmark

Updated May 25, 2026
Python

ParisaArbab / RL-Context-Selection

Star

RL for context-window selection in agent workflows: an agent decides which retrieved items to keep under a token budget. REINFORCE + PPO-lite trainers, from-scratch NumPy implementation with hand-derived, gradient-checked backprop, plus a PyTorch port validated against it via autograd cross-checks.

python machine-learning research reinforcement-learning numpy policy-gradient reinforce ppo reward-shaping context-window llm-agents rl-benchmark

Updated Aug 13, 2026
Python

Add this topic to your repo

To associate your repository with the rl-benchmark topic, visit your repo's landing page and select "manage topics."

Learn more