Stepan-Makarenko / ICM-PPO-implementation

Proximal Policy Optimization(PPO) with Intrinsic Curiosity Module(ICM) on Pyramid env, Unity ML

ICM-PPO-implementation

Experiment with ICM and PPO bunch for environment with sparse reward signal.

Description

The experiment tests the contribution of intrinsic reward to the agent's ability to solve the sparse-reward environment from Unity ML-Agents Toolkit.

Results

Tensorboard logs for extrinsic and intrinsic rewards

Running examples

Built With

• Unity ML-Agents Toolkit.