RAMario: Experimental Approach to Reptile Algorithm -- Reinforcement Learning for Mario
This research paper presents an experimental approach to using the Reptile algorithm for reinforcement learning to train a neural network to play Super Mario Bros. We implement the Reptile algorithm using the Super Mario Bros Gym library and TensorFlow in Python, creating a neural network model with a single convolutional layer, a flatten layer, and a dense layer. We define the optimizer and use the Reptile class to create an instance of the Reptile meta-learning algorithm. We train the model using multiple tasks and episodes, choosing actions using the current weights of the neural network model, taking those actions in the environment, and updating the model weights using the Reptile algorithm. We evaluate the performance of the algorithm by printing the total reward for each episode. In addition, we compare the performance of the Reptile algorithm approach to two other popular reinforcement learning algorithms, Proximal Policy Optimization (PPO) and Deep Q-Network (DQN), applied to the same Super Mario Bros task. Our results demonstrate that the Reptile algorithm provides a promising approach to few-shot learning in video game AI, with comparable or even better performance than the other two algorithms, particularly in terms of moves vs distance that agent performs for 1M episodes of training. The results shows that best total distance for world 1-2 in the game environment were ~1732 (PPO), ~1840 (DQN) and ~2300 (RAMario). Full code is available at https://github.com/s4nyam/RAMario.
Code (1)
Tasks
Few-Shot LearningMeta-Learningreinforcement-learningReinforcement LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Super Reinforcement Bros: Playing Super Mario Bros with Reinforcement Learning
We plan to apply and adjust some well-known reinforcement learning (RL) algorithms to train an automatic agent to play the 1985 Nintendo game Super Mario Bros under a speedrun rule. The agent may learn several control po…
Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)A novel meta-learning initialization method for physics-informed neural networks
Physics-informed neural networks (PINNs) have been widely used to solve various scientific computing problems. However, large training costs limit PINNs for some real-time applications. Although some works have been prop…
Meta-LearningEEG-Reptile: An Automatized Reptile-Based Meta-Learning Library for BCIs
Meta-learning, i.e., "learning to learn", is a promising approach to enable efficient BCI classifier training with limited amounts of data. It can effectively use collections of in some way similar classification tasks, …
EEGFew-Shot LearningMeta-LearningTransfer LearningBeyond The Rainbow: High Performance Deep Reinforcement Learning on a Desktop PC
Rainbow Deep Q-Network (DQN) demonstrated combining multiple independent enhancements could significantly boost a reinforcement learning (RL) agent's performance. In this paper, we present "Beyond The Rainbow" (BTR), a n…
Computational EfficiencyDeep Reinforcement LearningReinforcement Learning (RL)Improving End-to-End Speech-to-Intent Classification with Reptile
End-to-end spoken language understanding (SLU) systems have many advantages over conventional pipeline systems, but collecting in-domain speech data to train an end-to-end system is costly and time consuming. One questio…
ClassificationGeneral Classificationintent-classificationIntent Classification+4