vyass612
AI Security Researcher | Cardiff University | Alan Turing Institute | Airbus Group
Cardiff University
Pinned Repositories
neural-watchdog
A firewall for your *neural* networks.
dopamine
Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.
cage-challenge-1
cage-challenge-logical
dopamine
drl_backdoors_neural_activation_space
in-distribution_breakout
LNN
A `Neural = Symbolic` framework for sound and complete weighted real-value logic
LOA
Neuro-Symbolic Reinforcement Learning: Logical Optimal Action (LOA), a novel RL with Logical Neural Network (LNN) on text-based games
Option-Critic
A simple option critic framework using Q-Learning
vyass612's Repositories
vyass612/cage-challenge-1
vyass612/cage-challenge-logical
vyass612/dopamine
vyass612/drl_backdoors_neural_activation_space
vyass612/in-distribution_breakout
vyass612/LNN
A `Neural = Symbolic` framework for sound and complete weighted real-value logic
vyass612/LOA
Neuro-Symbolic Reinforcement Learning: Logical Optimal Action (LOA), a novel RL with Logical Neural Network (LNN) on text-based games
vyass612/Option-Critic
A simple option critic framework using Q-Learning