- A few implementations ranging from Navigation to Ping-pong using both on-policy and off-policy methods Algorithms used through these execrsises include DQN(Replay Buffer), Actor-Critic etcc.
Implementations of Rl algorithms ranging from Q-learning to Multi-Agent RL using DDPG in unity and gym environments.
Implementations of Rl algorithms ranging from Q-learning to Multi-Agent RL using DDPG in unity and gym environments.