Self-supervised Adversarial Imitation Learning

Abstract

Behavioural cloning is an imitation learning technique that teaches an agent how to behave via expert demonstrations. Recent approaches use self-supervision of fully-observable unlabelled snapshots of the states to decode state pairs into actions. However, the iterative learning scheme employed by these techniques is prone to get trapped into bad local minima. Previous work uses goal-aware strategies to solve this issue. However, this requires manual intervention to verify whether an agent has reached its goal. We address this limitation by incorporating a discriminator into the original framework, offering two key advantages and directly solving a learning problem previous work had. First, it disposes of the manual intervention requirement. Second, it helps in learning by guiding function approximation based on the state transition of the expert's trajectories. Third, the discriminator solves a learning issue commonly present in the policy model, which is to sometimes perform a `no ac

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keymonteiro2023self

Related papers

• Causal Confusion In Imitation Learning (2019)0.00
• Interactive And Hybrid Imitation Learning: Provably Beating Behavior Cloning (2024)0.00
• Discriminator Soft Actor Critic Without Extrinsic Rewards (2020)3.58
• Adversarial Soft Advantage Fitting: Imitation Learning Without Policy Optimization (2020)0.00
• Is Behavior Cloning All You Need? Understanding Horizon In Imitation Learning (2024)0.00
• Imitating Opponent To Win: Adversarial Policy Imitation Learning In Two-player Competitive Games (2022)0.00
• Preventing Imitation Learning With Adversarial Policy Ensembles (2020)0.00
• State-only Imitation With Transition Dynamics Mismatch (2020)0.00