Visual Transfer between Atari Games using Competitive Reinforcement Learning

2018-09-02 · Akshita Mittel, Sowmya Munukutla, Himanshi Yadav

This paper explores the use of deep reinforcement learning agents to transfer knowledge from one environment to another. More specifically, the method takes advantage of asynchronous advantage actor critic (A3C) architecture to generalize a target game using an agent trained on a source game in Atari. Instead of fine-tuning a pre-trained model for the target game, we propose a learning approach to update the model using multiple agents trained in parallel with different representations of the target game. Visual mapping between video sequences of transfer pairs is used to derive new representations of the target game; training on these visual representations of the target game improves model updates in terms of performance, data efficiency and stability. In order to demonstrate the functionality of the architecture, Atari games Pong-v0 and Breakout-v0 are being used from the OpenAI gym environment; as the source and target environment.

📄 PDF Abstract BibTeX arXiv:1809.00397

Code (1)

sowmya-mp/rl_a3c_pytorch 공식 구현 pytorch

Tasks

Atari GamesDeep Reinforcement LearningOpenAI Gym reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Visual Analogies between Atari Games for Studying Transfer Learning in RL

2018-07-29 · Doron Sobol, Lior Wolf, Yaniv Taigman

In this work, we ask the following question: Can visual analogies, learned in an unsupervised way, be used in order to transfer knowledge between pairs of games and even play one game using an agent trained for another g…

Atari Games Transfer Learning Visual Analogies

On Neural Consolidation for Transfer in Reinforcement Learning

2022-10-05 · Valentin Guillet, Dennis G. Wilson, Carlos Aguilar-Melchor, Emmanuel Rachelson

Although transfer learning is considered to be a milestone in deep reinforcement learning, the mechanisms behind it are still poorly understood. In particular, predicting if knowledge can be transferred between two given…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)+1

Decision Transformer vs. Decision Mamba: Analysing the Complexity of Sequential Decision Making in Atari Games

2024-12-01 · Ke Yan

This work analyses the disparity in performance between Decision Transformer (DT) and Decision Mamba (DM) in sequence modelling reinforcement learning tasks for different Atari games. The study first observed that DM gen…

Atari Games Decision Making Mamba Sequential Decision Making

Enhancing Two-Player Performance Through Single-Player Knowledge Transfer: An Empirical Study on Atari 2600 Games

2024-10-22 · Kimiya Saadat, Richard Zhao

Playing two-player games using reinforcement learning and self-play can be challenging due to the complexity of two-player environments and the possible instability in the training process. We propose that a reinforcemen…

Atari Games reinforcement-learning Reinforcement Learning Transfer Learning

Strategy and Benchmark for Converting Deep Q-Networks to Event-Driven Spiking Neural Networks

2020-09-30 · Weihao Tan, Devdhar Patel, Robert Kozma

Spiking neural networks (SNNs) have great potential for energy-efficient implementation of Deep Neural Networks (DNNs) on dedicated neuromorphic hardware. Recent studies demonstrated competitive performance of SNNs compa…

Atari Games Deep Reinforcement Learning image-classification Image Classification+3