-
Quantum-Computing Public
Toy models in Qiskit: Grover's algorithm with unknown number of solutions and arbitrary number of qubits
-
-
-
-
Basic-reinforcement-learning Public
Basic reinforcement learning algorithms with discrete state/action spaces and tile coding for continuous spaces
-
Policy-gradient-based-method Public
OpenAI-gym environment with REINFORCE
Python UpdatedJun 1, 2019 -
Implementation of MADDPG agents playing tennis
Python UpdatedMay 6, 2019 -
Continuous-PPO-single-agent Public
Straightforward implementation of vanilla PPO + optimization tricks in the "Reacher" environment
-
PPO-PyTorch Public
Forked from nikhilbarhate99/PPO-PyTorchSimple and beginner friendly implementation of Proximal Policy Optimization (PPO) in PyTorch
Python MIT License UpdatedApr 9, 2019 -
DDQN-PER agent on Udacity's banana collector environment