Reinforcement Learning
Questions
Topics
Off-policy Reinforcement Learning
Deep Reinforcement Learning
Pretraining for Reinforcement Learning
Recommended Reading
Reinforcement Learning: An Introduction
Deep Reinforcement Learning
Links to this note:
- Current Learning Objectives
- schwarzer2021pretraining: Pretraining Representations for Data-Efficient Reinforcement Learning
- Inbox
- Artificial Intelligence
- Actor Critic
- ChatGPT
- Incentive Salience
- Reinforcement Learning in the Brain
- Reproducibility in Science
- Predictive Processing
- Deep Reinforcement Learning
- Policy
- Off-policy Reinforcement Learning
- henderson2018deep: Deep Reinforcement Learning That Matters
- colombo2014deep: Deep and beautiful. The reward prediction error hypothesis of dopamine
- niv2009reinforcement: Reinforcement learning in the brain
- Dopamine
- Dopaminergic Neurons
- Bellman Equation
- Atari
- badia2020agent57: Agent57: Outperforming the Atari Human Benchmark
- barreto2018successor: Successor Features for Transfer in Reinforcement Learning
- dayan1993improving: Improving Generalization for Temporal Difference Learning: The Successor Representation
- jaderberg2017reinforcement: Reinforcement Learning with Unsupervised Auxiliary Tasks
- kearney2019making: Making Meaning: Semiotics Within Predictive Knowledge Architectures
- kostas2019asynchronous: Asynchronous Coagent Networks: Stochastic Networks for Reinforcement Learning without Backpropagation or a Clock
- machado2018revisiting: Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents
- Model-based RL
- Mountain Car
- Reinforcement Learning: An Introduction
- scholkopf2019causality: Causality for Machine Learning
- subramanian2020approximate: Approximate information state for approximate planning and reinforcement learning in partially observed systems
- sutton2011horde: Horde: A Scalable Real-time Architecture for Learning Knowledge from Unsupervised Sensorimotor Interaction
- Temporal Difference Learning
- veeriah2019discovery: Discovery of Useful Questions as Auxiliary Tasks
- wang2017learning: Learning to reinforcement learn
- white2015developing: Developing a predictive approach to knowledge
- Auxiliary Tasks
- white2017unifying: Unifying Task Specification in Reinforcement Learning
- vanhasselt2015learning: Learning to Predict Independent of Span
- Value Function
- Types of Learning
- Rich Sutton
- Reward
- mnih2016asynchronous: Asynchronous Methods for Deep Reinforcement Learning
- Markov Decisions Process
- liu2018breaking: Breaking the Curse of Horizon: Infinite-Horizon Off-Policy Estimation
- sutton1988learning: Learning to predict by the methods of temporal differences
- Experience Replay
- DeepMind Lab
- Behavior-Suite