This is an implementation of the Hierarchical Actor Critic (HAC) algorithm described in the paper, Learning Multi-Level Hierarchies with Hindsight (ICLR 2019), in PyTorch for OpenAI gym environments.
End-to-end deep reinforcement learning platform for Atari Breakout. Implements DQN, Double DQN, Dueling Networks, and Prioritized Experience Replay with side-by-side agent comparison, live inference, ...
We train the actor-critic policy with proximal policy optimization (PPO). For the IsaacGym simulation, we set dt = 0.01667 s with two simulation substeps. control_frequencyInv = 3 corresponds to a 20 ...
Integrating AI and computational neuroscience for mental health: neuroanalytic approaches to pattern detection and brain disorder diagnosis ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results