vanilla-policy-gradient

Here are 8 public repositories matching this topic...

Ehsan2754 / lunarlander_gym

This project is implementation of multiple AI agents based on different Reinforcement Learning methods to OpenAI Gymnasium Lunar-Lander environment which is classic rocket landing trajectory optimization problem.

reinforcement-learning deep-reinforcement-learning q-learning actor-critic vanilla-policy-gradient

Updated Dec 31, 2022
Python

iitimii / Gradient-Based-Reinforcement-Learning-Exploration

Star

Experimental exploration of gradient-based methods in RL. Features a simple naive algorithm derivation, REINFORCE implementation, in the CartPole environment. Bridges supervised and reinforcement learning paradigms

reinforcement-learning vanilla-policy-gradient

Updated Aug 31, 2024
Jupyter Notebook

kanji95 / Topics-in-Machine-Learning-CS7.502

Star

Topics in Machine Learning @ IIIT Hyderabad (Fall 2021)

policy-iteration value-iteration inverse-reinforcement-learning monte-carlo-methods actor-critic-methods td-methods vanilla-policy-gradient

Updated Apr 25, 2022
Jupyter Notebook

cbanerji / RL_implementations

Star

Pytorch implementation of classic and latest Model-Free RL algorithms.

reinforcement-learning soft-actor-critic vanilla-policy-gradient

Updated Aug 8, 2022
Python

nslyubaykin / relax_vpg_example

Star

Example VPG implementation with ReLAx

reinforcement-learning policy-gradient continuous-control actor-critic-methods discrete-control vanilla-policy-gradient

Updated Aug 29, 2022
Jupyter Notebook

Directorman9 / Gym-minigrid-games

Star

This notebook trains an agent to navigate a maze and reach a desired destination. It uses the Gym-MiniGrid's fourRoom-v0 environment as the maze. The agent is trained by using reiforcement learning's vanilla policy gradient (REINFORCE) algorithm.

reinforcement-learning gym minigrid reinforce vanilla-policy-gradient