patrik-ha / explainable-minichess
Chess environment for smaller chess variants, AlphaZero-like MCTS-learning, and Concept Detection
☆14Updated last year
Related projects ⓘ
Alternatives and complementary repositories for explainable-minichess
- ☆19Updated 7 months ago
- Causal Analysis of Agent Behavior for AI Safety☆17Updated last year
- A web based platform for collecting human actions in reinforcement learning environments☆26Updated last year
- Scaling scaling laws with board games.☆40Updated last year
- Explainable Reinforcement Learning (XRL) Resources☆33Updated last month
- Code for the paper "Understanding RL Vision"☆43Updated last year
- Interpreting how transformers simulate agents performing RL tasks☆69Updated last year
- Documentation for dynamic machine learning systems.☆27Updated last month
- Code for "Meta Learning Backpropagation And Improving It" @ NeurIPS 2021 https://arxiv.org/abs/2012.14905☆31Updated 2 years ago
- Understanding RL vision Distill article☆23Updated last year
- Repo to reproduce the First-Explore paper results☆36Updated last week
- INTeractive learning via REPresentatIon Discovery☆34Updated 5 months ago
- ☆17Updated last year
- ☆48Updated last year
- Automatically generate simple meta-learning tasks from a very large space☆15Updated last year
- ☆11Updated 2 years ago
- PyTorch Implementation of the paper "Towards Learning Abductive Reasoning using VSA Distributed Representations".☆12Updated 2 months ago
- ☆36Updated 2 years ago
- GPT implementation in Flax☆18Updated 2 years ago
- ☆12Updated 3 months ago
- ☆28Updated 2 years ago
- ☆45Updated last year
- ☆35Updated last year
- Supplementary Data for Evolving Reinforcement Learning Algorithms☆46Updated 3 years ago
- ☆26Updated 2 years ago
- Pytorch implementation on OpenAI's Procgen ppo-baseline, built from scratch.☆14Updated 5 months ago
- Minimum Description Length probing for neural network representations☆16Updated last week
- [AutoML'22] Bayesian Generational Population-based Training (BG-PBT)☆26Updated 2 years ago
- A neurosymbolic T5 agent for playing text games, from the EACL 2023 paper "Behavior Cloned Transformers are Neurosymbolic Reasoners"☆19Updated last year
- Evaluating different engineering tricks that make RL work☆15Updated 3 years ago