Reward Learning From Human Preferences And Demonstrations In Atari

Abstract

To solve complex real-world problems with reinforcement learning, we cannot rely on manually specified reward functions. Instead, we can have humans communicate an objective to the agent directly. In this work, we combine two approaches to learning from human feedback: expert demonstrations and trajectory preferences. We train a deep neural network to model the reward function and use its predicted reward to train an DQN-based deep reinforcement learning agent on 9 Atari games. Our approach beats the imitation learning baseline in 7 games and achieves strictly superhuman performance on 2 games without using game rewards. Additionally, we investigate the goodness of fit of the reward model, present some reward hacking problems, and study the effects of noise in the human labels.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyibarz2018reward

Related papers

• Playing Atari Games With Deep Reinforcement Learning And Human Checkpoint Replay (2016)0.00
• A Human Mixed Strategy Approach To Deep Reinforcement Learning (2018)7.50
• A Review For Deep Reinforcement Learning In Atari:benchmarks, Challenges, And Solutions (2021)0.00
• Model-based Reinforcement Learning For Atari (2019)0.00
• Safe Imitation Learning Via Fast Bayesian Reward Inference From Preferences (2020)0.00
• Is Deep Reinforcement Learning Really Superhuman On Atari? Leveling The Playing Field (2019)0.00
• Visual Transfer Between Atari Games Using Competitive Reinforcement Learning (2018)7.50
• Evaluating Agents Without Rewards (2020)0.00