-
### Method description
Constrained Generative Policy Optimization was introduced by Meta in a recent paper (https://arxiv.org/pdf/2409.20370). It seems to outperform PPO and DPO and is specifically…
-
Create and work inside folder `experimental/erc_5173_future_rewards`:
nFR allows owners to benefit from future price appreciation even after selling their tokens, without the need for market predic…
-
# Proposal: Proof-of-Consciousness Consensus Mechanism
**Summary:**
This proposal introduces a new consensus mechanism called Proof-of-Consciousness (PoC). Under PoC, only users who actively par…
-
### What client do you play on?
enUS
### Faction
Both
### Content Phase:
70
### Current Behaviour
[Design: Amulet of Flowing Life](https://wowgaming.altervista.org/aowow/?item=35202) ID:35202
…
-
Develop a hybrid attack decision-making system for agents that combines a Q-learning neural network (QNN) and rule-based constraints. This system will allow agents to dynamically decide between aggres…
-
## Business Description
An interface to allow anyone to create a GoodCollective pool smart contract without interacting with an explorer. The user will be able to complete the following steps:
1) …
-
Care should be taken to not fix typos in DB column names or similar.
desierialized -> deserialized
• contruct -> construct
• DkgPublicshares -> DkgPublicShares
• signaure -> signature
• atomicb…
-
As described in [the design doc](https://github.com/codex-storage/codex-research/blob/41c4b4409d2092d0a5475aca0f28995034e58d14/design/marketplace.md#repairs), the node that repairs a slot should be a…
AuHau updated
3 months ago
-
Different shapes for looking around the square might be possible.
* Maybe use a mask ? In tensorflow or in python
* For now the game state is 27 number, and it is **hard-coded**, which is bad for …
-
### Description
The project aims to develop a reinforcement learning (RL) agent to optimize waste collection in a simulated environment, minimizing overflow events and improving efficiency.
Environm…