akshilpatel
Reinforcement Learning Research Scientist. Research interests: Bounded rationality, intrinsic motivation and skill hierarchies in reinforcement learning
Pinned Repositories
ai_replications
Implementations of various machine learning algorithms.
BaRL-SimpleOptions
A small Python package which provides a simple framework for working with Reinforcement Learning Options.
centrality-experiments
Experiments for my MSc project in Hierarchical Reinforcement Learning
classification-spam
Classifying emails using basic supervised learning models
deeprl
gym
A toolkit for developing and comparing reinforcement learning algorithms.
hackathon
Code and resources for SixFifty's collaborative outreach projects (hackathons, student projects, etc).
hoc
Implementation of HIerarchical Option Critic (Riemer et al., 2018)
successor_representation
An exploration of the Successor Representation in Reinforcement Learning
tile-match-gym
Tile matching gym environment for reinforcement learning research.
akshilpatel's Repositories
akshilpatel/deeprl
akshilpatel/hoc
Implementation of HIerarchical Option Critic (Riemer et al., 2018)
akshilpatel/ai_replications
Implementations of various machine learning algorithms.
akshilpatel/BaRL-SimpleOptions
A small Python package which provides a simple framework for working with Reinforcement Learning Options.
akshilpatel/centrality-experiments
Experiments for my MSc project in Hierarchical Reinforcement Learning
akshilpatel/classification-spam
Classifying emails using basic supervised learning models
akshilpatel/gym
A toolkit for developing and comparing reinforcement learning algorithms.
akshilpatel/hackathon
Code and resources for SixFifty's collaborative outreach projects (hackathons, student projects, etc).
akshilpatel/Practical_DL
DL course co-developed by YSDA, HSE and Skoltech
akshilpatel/successor_representation
An exploration of the Successor Representation in Reinforcement Learning
akshilpatel/tile-match-gym
Tile matching gym environment for reinforcement learning research.
akshilpatel/Practical_RL
A course in reinforcement learning in the wild
akshilpatel/RNMGraphics
NONMEM graphics
akshilpatel/sac
Soft Actor-Critic
akshilpatel/sudoku-solver
Sudoku solver using inference followed by backtracking search as a backup!
akshilpatel/SynPath_Diabetes
SynPath module for generating type 2 diabetes pathway