DRL: Deep Reinforcement Learning for Intelligent Robot Control -- Concept, Literature, and Future

no code implementations • 20 Apr 2021 • Aras Dargazany

In this aspect, the high-level control creates the required intelligence for the control of the platform using the recorded low-level controlling data from that same platform generated by a trainer.

reinforcement-learning Reinforcement Learning (RL)

Model-based actor-critic: GAN (model generator) + DRL (actor-critic) => AGI

no code implementations • 4 Apr 2020 • Aras Dargazany

The proposed AI model is similar to (model-free) DDPG and therefore it's called model-based DDPG.

OpenAI Gym Unity

Iterative temporal differencing with fixed random feedback alignment support spike-time dependent plasticity in vanilla backpropagation for deep learning

no code implementations • ICLR 2018 • Aras Dargazany, Kunal Mankodiya

In vanilla backpropagation (VBP), activation function matters considerably in terms of non-linearity and differentiability.