karush17 / emix
Energy-based Surprise Minimization for Multi-Agent Value Factorization
☆12Updated last year
Related projects ⓘ
Alternatives and complementary repositories for emix
- Evolution-based Soft Actor-Critic (ESAC)☆41Updated 3 months ago
- Implementation of OpenAI's Evolution Strategies in PyTorch.☆20Updated 4 years ago
- Implementation of Eligibility Traces with Neural Networks in PyTorch and Tensorflow 2.0☆23Updated 3 years ago
- Hierarchical Attention in Reinforcement Learning for Stock Order Executions☆27Updated 3 years ago
- ☆29Updated 5 years ago
- Implementation of VALOR (Variational Option Discovery Algorithms)☆10Updated 5 years ago
- ☆18Updated 2 years ago
- Open source demo for the paper Learning to Score Behaviors for Guided Policy Optimization☆24Updated 4 years ago
- Implementation of "Sample-Efficient Deep Reinforcement Learning via Episodic Backward Update", NeurIPS 2019.☆16Updated 5 years ago
- Implementation of Tactical Optimistic and Pessimistic value estimation☆25Updated last year
- PyTorch IMPALA implementation☆24Updated 5 years ago
- Simple implementation of V-MPO proposed in https://arxiv.org/abs/1909.12238☆44Updated 4 years ago
- V-MPO torch version with DMLab30 and GTrXL☆12Updated 3 years ago
- Prioritized Sequence Experience Replay☆10Updated 3 years ago
- Implementation of Bootstrap DQN and Randomized Prior Functions on ALE☆52Updated 5 years ago
- Count based exploration with the successor representation for Unity ML's Pyramid☆12Updated 5 years ago
- A2C training of Relational Deep Reinforcement Learning Architecture☆13Updated 2 years ago
- Code for Sibling Rivalry and experiments presented in associated paper☆16Updated 3 years ago
- ☆40Updated 3 years ago
- Pytorch implementation of DreamerV2: MASTERING ATARI WITH DISCRETE WORLD MODELS☆50Updated 2 years ago
- ☆13Updated 3 years ago
- PyTorch implementation of Never Give Up: Learning Directed Exploration Strategies☆56Updated 3 years ago
- Code for Optimistic Exploration even with a Pessimistic Initialisation☆14Updated 4 years ago