Our AI hackathon brought together a diverse group of participants, who collaborated to develop a variety of impressive projects based on:
This event has now ended, but you can still register for upcoming events on lablab.ai. We look forward to seeing you at the next one!Checkout Upcoming Events →
Submissions from the teams participating in the Reinforcement Learning OpenAI Gym event and making it to the end 👊
RL Introductory Hackathon for envs Cartpole, Walker , Lunar Lander
3 environments, everything is good
Using the stable_baselines3 library, we tried to solve the problems proposed in the challenge. We used a Proximal Policy Optimization (PPO) Model. The Policy we used is a standard MLP. We tried to change the number of iteration to achieve a better performance.
We have completed 2 challenges. The first one (cartpole) was completed using our own code, we implemented Deep Q Learning. For the second one (Lunar Lander) we used stable_baseline library.
Applied reinforcement learning for agent to play these 3 games: Cartpole, LunarLander, BiPedal Walker. We used the basic model of Environment -> State -> Agent -> Action to train our agent. We reward the agent for achieving an outcome that we want, while penalizing the agent for doing otherwise. After many iterations, our agents learns to clear the games.
Used A2C and DQN for Lunar Lander DQN for Cartpole TQC for Bipedal Walker