aaksham / frozenlake
Value & Policy Iteration for the frozenlake environment of OpenAI
☆15Updated 5 years ago
Related projects: ⓘ
- A simple Gridworld environment for Open AI gym☆24Updated 6 years ago
- Implementation of Deep/Double Deep/Dueling Deep Q networks for playing Atari games using Keras and OpenAI gym☆40Updated 5 years ago
- Bayesian Uncertainty Exploration in Deep Reinforcement Learning☆17Updated 7 years ago
- Simple grid-world environment compatible with OpenAI-gym☆49Updated 4 years ago
- This repository contains the game bubble shooter as a gym environment. Based on: https://github.com/justinmeister/bubbleshooter☆17Updated 4 years ago
- TensorFlow implementation of Deep Reinforcement Learning papers☆28Updated 7 years ago
- AI learning to walk in gym's BipedalWalker environment.☆65Updated 7 years ago
- ☆18Updated 5 years ago
- TensorFlow A2C to solve Acrobot, with synchronized parallel environments☆35Updated 6 years ago
- Hindsight Experience Replay - Bit flipping experiment in Tensorflow☆57Updated 5 years ago
- ☆35Updated 6 years ago
- Reinforcement learning on gridworld with Q-learning☆9Updated 7 years ago
- The state-of-art deep rl algorithms for Montezuma's revenge☆25Updated 5 years ago
- [2019] (Neurips workshop paper) Blending behavioral cloning and RL☆9Updated last year
- Deep RL Bootcamp solutions☆35Updated 6 years ago
- Our NIPS 2017: Learning to Run source code☆56Updated last year
- PPO Dash: Improving Generalization in Deep Reinforcement Learning☆16Updated 5 years ago
- Code from my blog post & online course☆54Updated 5 years ago
- Code for experimenting with state and action abstractions in reinforcement learning.☆30Updated 3 years ago
- PyTorch implementation of Proximal Policy Optimization☆50Updated 6 years ago
- Combining deep learning and reinforcement learning.☆81Updated 2 years ago
- Scaling All-Goals Updates in Reinforcement Learning Using Convolutional Neural Networks☆41Updated 4 years ago
- A collection of code investigating the use of information theory for abstractions in RL☆15Updated 5 years ago
- Tensorflow implementation of Asynchronous Advantage Actor Critic (A3C) from "Asynchronous Methods for Deep Reinforcement Learning".☆25Updated 7 years ago
- Deep Developmental Reinforcement Learning☆29Updated 4 years ago
- Meta Reinforcement Learning Experiments☆33Updated 7 years ago
- Codebase of Santara et. al., RAIL: Risk Averse Imitation Learning, Published in AAMAS 2018☆14Updated 2 years ago
- An implementation of the A3C deep reinforcement learning method using a LSTM layer. Created with Tensorflow.☆29Updated 6 years ago
- Reinforcement learning algorithms with Generalized Advantage Estimation☆21Updated 6 years ago
- ☆35Updated this week