policy

RL_Project-Generalising_game_environments_with_curiosity-driven_agents

difra100 · PyTorch

or hover any field below to flag it

Overview

Name
RL_Project-Generalising_game_environments_with_curiosity-driven_agents
Author
difra100
Framework
PyTorch
License
MIT
Skill type
other
Evidence level
untested
Task description
Curiosity-driven RL agent trained on Atari games using the Intrinsic Curiosity Module (ICM) with PPO. Experiments compare intrinsic-only, extrinsic-only, and combined reward strategies on Phoenix, with few-shot transfer to Space Invaders.

Spaces

Action space
other · 0-dim · 0Hz
Observation space
  • type: other

Links

HuggingFace repo
null
Paper (arXiv)
null

Compatible robots

3+17 mentioned but not in catalog yet

Compatible environments

0

No environments list RL_Project-Generalising_game_environments_with_curiosity-driven_agents yet.

Datasets that reference this policy

0

No datasets reference RL_Project-Generalising_game_environments_with_curiosity-driven_agents yet.