PhD. candidate (Reinforcement Learning)
@raillabwits, University of the Witwatersrand
-
dqn_instruction_following Public
Simple deep Q-learning implemention for instruction following.
-
world-value-functions-prl Public
Code for the paper "World Value Functions: Knowledge Representation for Learning and Planning": https://prl-theworkshop.github.io/prl2022-icaps/papers/PRL2022_paper_10.pdf
-
rosarl Public
ROSARL: Reward-Only Safe Reinforcement Learning
-
manim Public
Forked from ManimCommunity/manimA community-maintained Python framework for creating mathematical animations.
Python MIT License UpdatedJan 30, 2023 -
boolean_composition Public
Code for the paper "A Boolean Task Algebra For Reinforcement Learning"
-
baselines Public
Forked from openai/baselinesOpenAI Baselines: high-quality implementations of reinforcement learning algorithms
Python MIT License UpdatedJun 16, 2022 -
compositional-rl-starter Public
Forked from lcswillems/rl-starter-filesRL starter files in order to immediatly train, visualize and evaluate an agent without writing any line of code
Python MIT License UpdatedOct 5, 2020 -
q-learning-with-options Public
Forked from s-mawjee/q-learning-with-optionsQ Learning with Options framework
Python GNU General Public License v3.0 UpdatedMay 23, 2019 -
inverse-reinforcement-learning Public
Forked from s-mawjee/inverse-reinforcement-learningInverse Reinforcement Learning Algorithms
Python MIT License UpdatedMay 23, 2019 -