Generative Adversarial Imitation Learning.pdf

N/A

Generative Adversarial Imitation Learning Jonathan Ho Stefano Ermon OpenAI Stanford University hoj@openai.com ermon@cs.stanford.edu Abstract Consider learning a policy from example expert behavior, without interaction with the expert or access to a reinforcement signal. One approach is to recover the expert’s cost function with inverse reinforcement learning, then extract…

related reading

• Generative Adversarial Imitation Learningarxiv.org
• 1011.0686arxiv.org
• Ch. 21 - Imitation Learningunderactuated.mit.edu
• Reinforcement Learning via Implicit Imitation Guidancearxiv.org
• Flow Matching Policy Gradientsflowreinforce.github.io
• Key Papers in Deep RL - Spinning Up documentationspinningup.openai.com
• [1707.06347] Proximal Policy Optimization Algorithmsarxiv.org
• [2606.09758] Difference-Aware Retrieval Policies for Imitation Learningarxiv.org
• InfoGAIL: Interpretable Imitation Learning from Visual Demonstrationsarxiv.org
• Should I Use Offline RL or Imitation Learning? – The Berkeley Artificial Intelligence Research Blogbair.berkeley.edu
• Contrastive Learning as Goal-Conditioned Reinforcement Learningarxiv.org
• Imitating Latent Policies from Observationarxiv.org