README.md

metadata

license: mit
pipeline_tag: reinforcement-learning
tags:
  - Memory Gym
  - Proximal Policy Optimization
  - Transformer-XL
  - CleanRL

Pre-trained models that work with CleanRL's PPO-TrXL implementation and the environments of Memory Gym. Usage via enjoy.py found here.

Original Paper and Implementation

• Memory Gym: Towards Endless Tasks to Benchmark Memory Capabilities of Agents
• neroRL, Episodic Transformer Memory PPO
• Interactive Visualizations of Trained Agents

Related Publications and Repositories

• Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
• Stabilizing Transformers for Reinforcement Learning
• Towards mental time travel: a hierarchical memory for reinforcement learning agents
• Grounded Language Learning Fast and Slow
• transformerXL_PPO_JAX