Plan-to-Explore implementation in PyTorch (Again)

Plan-to-explore

This repo implements the Plan-to-explore algorithm from Planning to Explore via Self-Supervised World Models based on the PlaNet-Pytorch. It has been confirmed working on the DeepMind Control Suite/MuJoCo environment. Hyperparameters have been taken from the paper.

Installation

To install all dependencies with Anaconda run using the following commands. Firstly use conda.

pip install -r requirements.txt

Training (e.g. DMC walker-walk zero-shot)

Zero-shot

python main.py --algo p2e --env walker-walk --action-repeat 2 --id name-of-experiement --zero-shot

Few-shot

python main.py --algo p2e --env walker-walk --action-repeat 2 --id name-of-experiement

For best performance with DeepMind Control Suite, try setting environment variable MUJOCO_GL=egl (see instructions and details here).

We used weights and biases for logging the runs.

You can see the performance from the zero-shot/few-shot trained policy on the test/episode_reward.

Links

• Planning to Explore via Self-Supervised World Models
• ramanans/plan2explore