google-deepmind / pycolab
A highly-customisable gridworld game engine with some batteries included. Make your own gridworld games to test reinforcement learning agents!
☆657Updated 5 years ago
Alternatives and similar repositories for pycolab:
Users that are interested in pycolab are comparing it to the libraries listed below
- PlayGround: AI Research into Multi-Agent Learning.☆768Updated last year
- Code for the paper "Meta-Learning Shared Hierarchies"☆611Updated last year
- A TensorFlow implementation of Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures.☆995Updated 5 years ago
- Efficient Batched Reinforcement Learning in TensorFlow☆965Updated 6 years ago
- This is a suite of reinforcement learning environments illustrating various safety properties of intelligent agents.☆611Updated 2 years ago
- Code for the paper "Emergent Complexity via Multi-agent Competition"☆807Updated last year
- Hacks for training RL systems from John Schulman's lecture at Deep RL Bootcamp (Aug 2017)☆1,105Updated 7 years ago
- hanabi_learning_environment is a research platform for Hanabi experiments.☆649Updated 2 years ago
- Code for the paper "Quantifying Transfer in Reinforcement Learning"☆397Updated last year
- Implementation of TRPO and related algorithms☆625Updated 6 years ago
- Trust Region Policy Optimization with TensorFlow and OpenAI Gym☆361Updated 4 years ago
- RUDDER for ATARI games with delayed rewards in OpenAI Baselines package☆266Updated 5 years ago
- [ICML 2017] TensorFlow code for Curiosity-driven Exploration for Deep Reinforcement Learning☆1,423Updated 2 years ago
- Code for the paper "Curiosity-driven Exploration in Deep Reinforcement Learning via Bayesian Neural Networks"☆341Updated 6 years ago
- Code for the paper "Exploration by Random Network Distillation"☆888Updated 4 years ago
- lagom: A PyTorch infrastructure for rapid prototyping of reinforcement learning algorithms.☆374Updated 2 years ago
- Implementation of Meta-RL A3C algorithm☆402Updated 7 years ago
- World Models☆441Updated 4 years ago
- Spriteworld: a flexible, configurable python-based reinforcement learning environment☆369Updated 4 years ago
- Code for the paper "Evolution Strategies as a Scalable Alternative to Reinforcement Learning"☆1,581Updated 5 years ago
- ☆303Updated last year
- Code for the paper "Generative Adversarial Imitation Learning"☆700Updated 6 years ago
- Reinforcement Learning with Deep Energy-Based Policies☆417Updated last year
- Hybrid CPU/GPU implementation of the A3C algorithm for deep reinforcement learning.☆658Updated 4 years ago
- Velocity in deep-learning research☆276Updated 2 years ago
- World Models Experiments☆634Updated 2 years ago
- An implementation of the ideas from this paper https://arxiv.org/pdf/1803.10122.pdf☆283Updated 2 years ago
- Persistent advantage learning dueling double DQN for the Arcade Learning Environment☆264Updated 7 years ago
- Neural network model, suitable for multi-agent learning. https://arxiv.org/abs/1605.07736☆213Updated 8 years ago
- ☆117Updated 4 years ago