irl-imitation

Differences from forked repo

• Fixed issue yrlu#1
• Implemented parallel value iteration and state visitation frequency calculation (numpy, CPU
• Implemented value iteration and state visitation in tensorflow (GPU, greatly enhances speed!)
• Implemented expected value difference evaluation metric (https://github.com/MatthewJA/Inverse-Reinforcement-Learning/blob/master/irl/maxent.py#L208)

Implementations of some model-based Inverse Reinforcement Learning (IRL) algorithms in python/Tensorflow. Mainly for educational purpose. (WIP)

python demo.py

Algorithms implemented

• Linear inverse reinforcement learning (Ng & Russell 2000)
• Maximum entropy inverse reinforcement learning (Ziebart et al. 2008)
• Maximum entropy deep inverse reinforcement learning (Wulfmeier et al. 2015)

MDP & solver implemented

• gridworld 2D
• gridworld 1D
• value iteration

Dependencies

• python 2.7
• cvxopt
• Tensorflow 0.12.1
• matplotlib

Linear Inverse Reinforcement Learning

• Following Ng & Russell 2000 paper: Algorithms for Inverse Reinforcement Learning, algorithm 1

$ python linear_irl_gridworld.py --act_random=0.3 --gamma=0.5 --l1=10 --r_max=10

Maximum Entropy Inverse Reinforcement Learning

(This implementation is largely influenced by Matthew Alger's maxent implementation)

• Following Ziebart et al. 2008 paper: Maximum Entropy Inverse Reinforcement Learning
• $ python maxent_irl_gridworld.py --help for options descriptions

$ python maxent_irl_gridworld.py --height=10 --width=10 --gamma=0.8 --n_trajs=100 --l_traj=50 --no-rand_start --learning_rate=0.01 --n_iters=20

$ python maxent_irl_gridworld.py --gamma=0.8 --n_trajs=400 --l_traj=50 --rand_start --learning_rate=0.01 --n_iters=20

Maximum Entropy Deep Inverse Reinforcement Learning

• Following Wulfmeier et al. 2015 paper: Maximum Entropy Deep Inverse Reinforcement Learning. FC version implemented. The implementation does not follow exactly the model proposed in the paper. Some tweaks applied including elu activations, clipping gradients, l2 regularization etc.
• $ python deep_maxent_irl_gridworld.py --help for options descriptions

$ python deep_maxent_irl_gridworld.py --learning_rate=0.02 --n_trajs=200 --n_iters=20

MIT License