ZainBashir / Solving-openAI-Gym-MountainCarProblem-using-DQN-with-Image-inputLinks
I have targeted to solve the benchmark problem in Reinforcement learning literature using Deep Q-networks with images as the only input to the model. Keras was used to model the Convolutional neural network which predicts the best action to take in a given state
☆12Updated 5 years ago
Alternatives and similar repositories for Solving-openAI-Gym-MountainCarProblem-using-DQN-with-Image-input
Users that are interested in Solving-openAI-Gym-MountainCarProblem-using-DQN-with-Image-input are comparing it to the libraries listed below
Sorting:
- The code and the trained model for A Deep Q-Network for Robotic Odor/Gas Source Localization: Modeling, Measurement and Comparative Study☆7Updated last year
- Contains implementations of various deep RL algorithms and papers including action conditional video prediction | Python | Tensorflow | O…☆7Updated 7 years ago
- Using N-step dueling DDQN with PER for playing Pacman game☆22Updated 5 years ago
- Deep Q-Network (DQN) and DDPG to address the problem of stall around the wing sail of an autonomous sailing robot☆11Updated 6 years ago
- Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agents☆8Updated 3 years ago
- ☆11Updated 3 years ago
- Autonomous visual navigation using the depth images☆11Updated 5 years ago
- ReinforcementLearning Learn Play Atari Using DDPG and LSTM.☆20Updated 7 years ago
- coach的rl练习，主要有q_learning,sarsa,REINFORCE,DQN,Actor-Critic,DDPG,使用tensorflow2.0编写☆9Updated 5 years ago
- Implementation of Deep Deterministic Policy Gradient (DDPG) with Prioritized Experience Replay (PER)☆51Updated 3 months ago
- Dueling DQN Pytorch☆13Updated 3 years ago
- A simple and fast 2D RL environment with obstacles to learn navigation.☆21Updated 5 years ago
- Multi Agent adaptation of Soft Actor Critic Reinforcement Learning Algorithm☆19Updated 6 years ago
- ☆11Updated 2 years ago
- 通过python3.6编程，利用DQN算法实现机器学习避开障碍走到迷宫终点。（Through python3.6 programming, I use DQN algorithm to achieve machine learning and avoid obstacles…☆10Updated 7 years ago
- This repo implements Deep Q-Network (DQN) for solving the Frozenlake-v1 environment of the Gymnasium library using Python 3.8 and PyTorch…☆18Updated last year
- Deep recurrent Q learning on CartPole-v1 environment☆91Updated last year
- meta-MADDPG (Python implementation)☆18Updated 6 years ago
- 用DDPG/MADDPG/DQN/MADDPG+advantage实验 OpenAI开源的MPE环境☆24Updated 6 years ago
- Use deep Q network to solve maze problem generated randomly, i.e. find the shortest path in a maze☆8Updated 2 years ago
- The implementation of LSTM-TD3.☆81Updated 2 years ago
- PyTorch implementation of discrete version of Soft Actor-Critic.☆34Updated 3 years ago
- Pytorch Implement DRL algorithms (A2C, DDPG, PPO, TD3, SAC) for continuous action space control tasks.☆19Updated 5 years ago
- ☆13Updated 2 years ago
- Adaptation of DQN, DDQN and COMA for multi-agent Gym environments☆12Updated last year
- ☆8Updated 2 years ago
- Dueling Double Deep Q Network with Prioritized Experience Replay Memory☆10Updated 2 years ago
- code for "Decoupled Preference-based Reinforcement Learning for Personalized Human-Robot Interaction"☆10Updated 2 years ago
- Here is our algorithm for Pursuit Problem based on the Distributed Reinforcement Learning for Cooperative Multi-robot Pursuit☆10Updated 6 years ago
- [TNNLS] PGDQN: A generalized and efficient preference-guided epsilon-greedy policy equipped DQN for Atari and Autonomous Driving☆12Updated last year