policy

BipedalWalker-v3-DDPG-Agent-with-Real-Time-Visual-Learning

GMRicks · PyTorch

or hover any field below to flag it

Overview

Name
BipedalWalker-v3-DDPG-Agent-with-Real-Time-Visual-Learning
Author
GMRicks
Framework
PyTorch
License
unknown
Skill type
locomotion
Evidence level
untested
Task description
Train a Soft Actor-Critic (SAC) agent to master the BipedalWalker-v3 environment. This end-to-end RL solution features robust actor-critic networks, a replay buffer, and real-time visual demos to showcase the agent’s continuous control performance and learning process.

Spaces

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

Links

HuggingFace repo
null
Paper (arXiv)
null

Compatible robots

0+20 mentioned but not in catalog yet

No robots list BipedalWalker-v3-DDPG-Agent-with-Real-Time-Visual-Learning as compatible yet. Know of one? Flag it above.

Compatible environments

0

No environments list BipedalWalker-v3-DDPG-Agent-with-Real-Time-Visual-Learning yet.

Datasets that reference this policy

0

No datasets reference BipedalWalker-v3-DDPG-Agent-with-Real-Time-Visual-Learning yet.